github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #12640] ollama hanging #34151

New Issue
Closed
opened 2026-04-22 17:28:18 -05:00 by GiteaMirror · 24 comments
GiteaMirror commented 2026-04-22 17:28:18 -05:00
Owner
Copy Link

Originally created by @samialisayed on GitHub (Oct 15, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12640

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

Ollama is hanging when I send a message and not getting any response. this happens with all models. Any idea how to solve this. Ollama was working fine a month ago. I do not know what happened!!

Relevant log output

OS

Windows

GPU

Tesla T4

CPU

No response

Ollama version

v0.12.5

Originally created by @samialisayed on GitHub (Oct 15, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12640 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? Ollama is hanging when I send a message and not getting any response. this happens with all models. Any idea how to solve this. Ollama was working fine a month ago. I do not know what happened!! ### Relevant log output ```shell ``` ### OS Windows ### GPU Tesla T4 ### CPU _No response_ ### Ollama version v0.12.5
GiteaMirror added the bugwindows labels 2026-04-22 17:28:18 -05:00
GiteaMirror commented 2026-04-22 17:28:22 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Oct 15, 2025):

@samialisayed may I ask which model you are running. Sorry about that!

<!-- gh-comment-id:3407799791 --> @jmorganca commented on GitHub (Oct 15, 2025): @samialisayed may I ask which model you are running. Sorry about that!
GiteaMirror commented 2026-04-22 17:28:23 -05:00
Author
Owner
Copy Link

@samialisayed commented on GitHub (Oct 15, 2025):

@jmorganca
I tried many models such as llama3, tinyllama, phi

<!-- gh-comment-id:3407826053 --> @samialisayed commented on GitHub (Oct 15, 2025): @jmorganca I tried many models such as llama3, tinyllama, phi
GiteaMirror commented 2026-04-22 17:28:23 -05:00
Author
Owner
Copy Link

@kappa8219 commented on GitHub (Oct 17, 2025):

see #12660 fixed in 0.12.6

<!-- gh-comment-id:3414193615 --> @kappa8219 commented on GitHub (Oct 17, 2025): see #12660 fixed in 0.12.6
GiteaMirror commented 2026-04-22 17:28:24 -05:00
Author
Owner
Copy Link

@samialisayed commented on GitHub (Oct 17, 2025):

@kappa8219 it is not fixed. it is still hanging

<!-- gh-comment-id:3415900031 --> @samialisayed commented on GitHub (Oct 17, 2025): @kappa8219 it is not fixed. it is still hanging
GiteaMirror commented 2026-04-22 17:28:24 -05:00
Author
Owner
Copy Link

@kappa8219 commented on GitHub (Oct 17, 2025):

@kappa8219 it is not fixed. it is still hanging

Strange, I got same GPU, maybe node is different.

<!-- gh-comment-id:3415926136 --> @kappa8219 commented on GitHub (Oct 17, 2025): > @kappa8219 it is not fixed. it is still hanging Strange, I got same GPU, maybe node is different.
GiteaMirror commented 2026-04-22 17:28:25 -05:00
Author
Owner
Copy Link

@samialisayed commented on GitHub (Oct 17, 2025):

@kappa8219 do you recommend any solution?

<!-- gh-comment-id:3416052797 --> @samialisayed commented on GitHub (Oct 17, 2025): @kappa8219 do you recommend any solution?
GiteaMirror commented 2026-04-22 17:28:25 -05:00
Author
Owner
Copy Link

@kappa8219 commented on GitHub (Oct 17, 2025):

@kappa8219 do you recommend any solution?

No, for OS Windows none. At Linux would try to get system logs.

<!-- gh-comment-id:3416061464 --> @kappa8219 commented on GitHub (Oct 17, 2025): > @kappa8219 do you recommend any solution? No, for OS Windows none. At Linux would try to get system logs.
GiteaMirror commented 2026-04-22 17:28:26 -05:00
Author
Owner
Copy Link

@katmandoo212 commented on GitHub (Oct 17, 2025):

Same issue. Tried several models including gpt-oss:20b downloaded to my PC today.

ollama --version
ollama version is 0.12.6

ollama run qwen3:1.7b "What is the equation to calculate the area of a sqaure?"

ollama serve
time=2025-10-17T17:39:29.977-04:00 level=INFO source=routes.go:1511 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:G:\OllamaFiles\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]"
time=2025-10-17T17:39:30.041-04:00 level=INFO source=images.go:522 msg="total blobs: 330"
time=2025-10-17T17:39:30.075-04:00 level=INFO source=images.go:529 msg="total unused blobs removed: 0"
time=2025-10-17T17:39:30.087-04:00 level=INFO source=routes.go:1564 msg="Listening on 127.0.0.1:11434 (version 0.12.6)"
time=2025-10-17T17:39:30.090-04:00 level=INFO source=runner.go:80 msg="discovering available GPUs..."
time=2025-10-17T17:39:30.878-04:00 level=INFO source=types.go:129 msg="inference compute" id=cpu library=cpu compute="" name=cpu description=cpu libdirs=ollama driver="" pci_id="" type="" total="11.9 GiB" available="8.1 GiB"
time=2025-10-17T17:39:30.878-04:00 level=INFO source=routes.go:1605 msg="entering low vram mode" "total vram"="0 B" threshold="20.0 GiB"
[GIN] 2025/10/17 - 17:39:45 | 200 | 603.2µs | 127.0.0.1 | HEAD "/"
[GIN] 2025/10/17 - 17:39:45 | 200 | 221.7137ms | 127.0.0.1 | POST "/api/show"

<!-- gh-comment-id:3417349372 --> @katmandoo212 commented on GitHub (Oct 17, 2025): Same issue. Tried several models including gpt-oss:20b downloaded to my PC today. ollama --version ollama version is 0.12.6 ollama run qwen3:1.7b "What is the equation to calculate the area of a sqaure?" ollama serve time=2025-10-17T17:39:29.977-04:00 level=INFO source=routes.go:1511 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:G:\\OllamaFiles\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]" time=2025-10-17T17:39:30.041-04:00 level=INFO source=images.go:522 msg="total blobs: 330" time=2025-10-17T17:39:30.075-04:00 level=INFO source=images.go:529 msg="total unused blobs removed: 0" time=2025-10-17T17:39:30.087-04:00 level=INFO source=routes.go:1564 msg="Listening on 127.0.0.1:11434 (version 0.12.6)" time=2025-10-17T17:39:30.090-04:00 level=INFO source=runner.go:80 msg="discovering available GPUs..." time=2025-10-17T17:39:30.878-04:00 level=INFO source=types.go:129 msg="inference compute" id=cpu library=cpu compute="" name=cpu description=cpu libdirs=ollama driver="" pci_id="" type="" total="11.9 GiB" available="8.1 GiB" time=2025-10-17T17:39:30.878-04:00 level=INFO source=routes.go:1605 msg="entering low vram mode" "total vram"="0 B" threshold="20.0 GiB" [GIN] 2025/10/17 - 17:39:45 | 200 | 603.2µs | 127.0.0.1 | HEAD "/" [GIN] 2025/10/17 - 17:39:45 | 200 | 221.7137ms | 127.0.0.1 | POST "/api/show"
GiteaMirror commented 2026-04-22 17:28:26 -05:00
Author
Owner
Copy Link

@mkrostm commented on GitHub (Oct 17, 2025):

Same issue. with all models, deepseek-r1:1.5b, llama3.2, qwen2.5
ollama version is 0.12.6
windows 10

<!-- gh-comment-id:3417512070 --> @mkrostm commented on GitHub (Oct 17, 2025): Same issue. with all models, deepseek-r1:1.5b, llama3.2, qwen2.5 ollama version is 0.12.6 windows 10
GiteaMirror commented 2026-04-22 17:28:27 -05:00
Author
Owner
Copy Link

@Panican-Whyasker commented on GitHub (Oct 19, 2025):

Same issue here. Ollama 0.12.6 on Windows 11, GPU nVidia GeForce 840M (CUDA compute capability 5.0, the minimum required by Ollama) with 2 GB of VRAM; CPU Intel Core i7-5600, 6 GB system RAM. Therefore, have tried only rather small LLMs like gemma3:270m and qwen3:1.7b. Trying to start the LLMs in either PowerShell or inside Ollama's GUI - same result: The model start takes forever. At the same time, one ollama.exe process keeps running at 25% CPU (which is one of four logical cores running at 100%). Looked at the process' threads with SysInternals Process Explorer, see attached screenshot.

Image

Here is my server log:

time=2025-10-19T12:39:08.441+02:00 level=INFO source=routes.go:1511 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\Users\Joro\.ollama\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]"
time=2025-10-19T12:39:08.447+02:00 level=INFO source=images.go:522 msg="total blobs: 12"
time=2025-10-19T12:39:08.447+02:00 level=INFO source=images.go:529 msg="total unused blobs removed: 0"
time=2025-10-19T12:39:08.450+02:00 level=INFO source=routes.go:1564 msg="Listening on 127.0.0.1:11434 (version 0.12.6)"
time=2025-10-19T12:39:08.453+02:00 level=INFO source=runner.go:80 msg="discovering available GPUs..."
time=2025-10-19T12:39:10.284+02:00 level=INFO source=types.go:112 msg="inference compute" id=GPU-838173db-880d-6d37-e6ad-d4b277cdde5a library=CUDA compute=5.0 name=CUDA0 description="NVIDIA GeForce 840M" libdirs=ollama,cuda_v12 driver=13.0 pci_id=03:00.0 type=discrete total="2.0 GiB" available="2.0 GiB"
time=2025-10-19T12:39:10.285+02:00 level=INFO source=routes.go:1605 msg="entering low vram mode" "total vram"="2.0 GiB" threshold="20.0 GiB"
[GIN] 2025/10/19 - 12:39:10 | 200 | 522.6µs | 127.0.0.1 | HEAD "/"
[GIN] 2025/10/19 - 12:39:10 | 200 | 3.7394ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2025/10/19 - 12:43:09 | 200 | 0s | 127.0.0.1 | HEAD "/"
[GIN] 2025/10/19 - 12:43:09 | 200 | 117.6405ms | 127.0.0.1 | POST "/api/show"

And that's it. Ollama.exe (one of two copies in memory) keeps running at 25% CPU (100% of one logical core).

Image

When trying to run the same model from within Ollama's GUI, the server log gets a few extra lines:

time=2025-10-19T12:54:34.628+02:00 level=INFO source=routes.go:1511 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\Users\Joro\.ollama\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]"
time=2025-10-19T12:54:34.643+02:00 level=INFO source=images.go:522 msg="total blobs: 12"
time=2025-10-19T12:54:34.657+02:00 level=INFO source=images.go:529 msg="total unused blobs removed: 0"
time=2025-10-19T12:54:34.673+02:00 level=INFO source=routes.go:1564 msg="Listening on 127.0.0.1:11434 (version 0.12.6)"
time=2025-10-19T12:54:34.675+02:00 level=INFO source=runner.go:80 msg="discovering available GPUs..."
time=2025-10-19T12:54:37.090+02:00 level=INFO source=types.go:112 msg="inference compute" id=GPU-838173db-880d-6d37-e6ad-d4b277cdde5a library=CUDA compute=5.0 name=CUDA0 description="NVIDIA GeForce 840M" libdirs=ollama,cuda_v12 driver=13.0 pci_id=03:00.0 type=discrete total="2.0 GiB" available="2.0 GiB"
time=2025-10-19T12:54:37.091+02:00 level=INFO source=routes.go:1605 msg="entering low vram mode" "total vram"="2.0 GiB" threshold="20.0 GiB"
[GIN] 2025/10/19 - 12:54:37 | 200 | 525.5µs | 127.0.0.1 | GET "/api/version"
[GIN] 2025/10/19 - 12:54:37 | 200 | 525.5µs | 127.0.0.1 | GET "/api/version"
[GIN] 2025/10/19 - 12:54:37 | 200 | 5.7471ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2025/10/19 - 12:54:37 | 200 | 160.8987ms | 127.0.0.1 | POST "/api/show"
[GIN] 2025/10/19 - 12:54:44 | 200 | 0s | 127.0.0.1 | GET "/api/version"
[GIN] 2025/10/19 - 12:54:44 | 200 | 6.6484ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2025/10/19 - 12:54:56 | 200 | 124.4086ms | 127.0.0.1 | POST "/api/show"
[GIN] 2025/10/19 - 12:54:56 | 200 | 100.1837ms | 127.0.0.1 | POST "/api/show"

Image

And here's my app.log:

time=2025-10-19T12:54:32.717+02:00 level=INFO source=app_windows.go:272 msg="starting Ollama" app=C:\Users\Joro\AppData\Local\Programs\Ollama version=0.12.6 OS=Windows/10.0.26100
time=2025-10-19T12:54:32.721+02:00 level=INFO source=app.go:232 msg="initialized tools registry" tool_count=0
time=2025-10-19T12:54:32.735+02:00 level=INFO source=app.go:247 msg="starting ollama server"
time=2025-10-19T12:54:33.173+02:00 level=INFO source=app.go:279 msg="starting ui server" port=56109
time=2025-10-19T12:54:35.437+02:00 level=INFO source=ui.go:171 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=997.1µs request_id=1760871275436712400 version=0.12.6
time=2025-10-19T12:54:35.471+02:00 level=INFO source=ui.go:171 msg=site.serveHTTP http.method=GET http.path=/api/v1/chats http.pattern="GET /api/v1/chats" http.status=200 http.d=1.0016ms request_id=1760871275470420900 version=0.12.6
time=2025-10-19T12:54:35.490+02:00 level=INFO source=ui.go:171 msg=site.serveHTTP http.method=GET http.path=/api/v1/me http.pattern="GET /api/v1/me" http.status=200 http.d=121.4562ms request_id=1760871275368774800 version=0.12.6
time=2025-10-19T12:54:36.039+02:00 level=ERROR source=ui.go:1617 msg="failed to get inference compute" error="timeout scanning server log for inference compute details"
time=2025-10-19T12:54:36.039+02:00 level=ERROR source=ui.go:171 msg=site.serveHTTP error="failed to get inference compute: timeout scanning server log for inference compute details" http.method=GET http.path=/api/v1/inference-compute http.pattern="GET /api/v1/inference-compute" http.status=500 http.d=592.3808ms request_id=1760871275447595400 version=0.12.6
time=2025-10-19T12:54:36.174+02:00 level=INFO source=updater.go:252 msg="beginning update checker" interval=1h0m0s
time=2025-10-19T12:54:37.091+02:00 level=INFO source=ui.go:171 msg=site.serveHTTP http.method=GET http.path=/api/v1/health http.pattern="GET /api/v1/health" http.status=200 http.d=1.6225602s request_id=1760871275469340400 version=0.12.6
time=2025-10-19T12:54:37.098+02:00 level=INFO source=ui.go:171 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=1.6539439s request_id=1760871275444706100 version=0.12.6
time=2025-10-19T12:54:37.187+02:00 level=INFO source=server.go:343 msg=Matched "inference compute"="{Library:CUDA Variant: Compute:5.0 Driver:13.0 Name:CUDA0 VRAM:2.0 GiB}"
time=2025-10-19T12:54:37.187+02:00 level=INFO source=ui.go:171 msg=site.serveHTTP http.method=GET http.path=/api/v1/inference-compute http.pattern="GET /api/v1/inference-compute" http.status=200 http.d=128.9369ms request_id=1760871277058569100 version=0.12.6
time=2025-10-19T12:54:37.253+02:00 level=INFO source=ui.go:171 msg=site.serveHTTP http.method=GET http.path=/api/v1/model/gemma3:270m/capabilities http.pattern="GET /api/v1/model/{model}/capabilities" http.status=200 http.d=1.7391883s request_id=1760871275514116200 version=0.12.6
time=2025-10-19T12:54:37.293+02:00 level=INFO source=ui.go:171 msg=site.serveHTTP http.method=POST http.path=/api/v1/model/upstream http.pattern="POST /api/v1/model/upstream" http.status=200 http.d=161.3473ms request_id=1760871277131674100 version=0.12.6
time=2025-10-19T12:54:40.146+02:00 level=INFO source=ui.go:171 msg=site.serveHTTP http.method=GET http.path=/api/v1/chat/0199fbf4-fbea-7735-85af-904746282010 http.pattern="GET /api/v1/chat/{id}" http.status=200 http.d=15.5374ms request_id=1760871280131187300 version=0.12.6
time=2025-10-19T12:54:42.095+02:00 level=INFO source=ui.go:171 msg=site.serveHTTP http.method=GET http.path=/api/v1/chat/0199fbf4-fbea-7735-85af-904746282010 http.pattern="GET /api/v1/chat/{id}" http.status=200 http.d=507.5µs request_id=1760871282095350400 version=0.12.6
time=2025-10-19T12:54:44.635+02:00 level=INFO source=ui.go:171 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=950.6µs request_id=1760871284634242300 version=0.12.6
time=2025-10-19T12:54:44.639+02:00 level=INFO source=ui.go:171 msg=site.serveHTTP http.method=GET http.path=/api/v1/chat/0199fbf4-fbea-7735-85af-904746282010 http.pattern="GET /api/v1/chat/{id}" http.status=200 http.d=1.9311ms request_id=1760871284637210500 version=0.12.6
time=2025-10-19T12:54:44.646+02:00 level=INFO source=ui.go:171 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=10.3327ms request_id=1760871284636351800 version=0.12.6
time=2025-10-19T12:57:50.812+02:00 level=ERROR source=ui.go:1178 msg="chat stream error" error="Post "http://127.0.0.1:11434/api/chat": context canceled"
time=2025-10-19T12:57:50.814+02:00 level=INFO source=ui.go:171 msg=site.serveHTTP http.method=POST http.path=/api/v1/chat/0199fbf4-fbea-7735-85af-904746282010 http.pattern="POST /api/v1/chat/{id}" http.status=200 http.d=2m54.1014868s request_id=1760871296712971700 version=0.12.6
time=2025-10-19T12:57:50.878+02:00 level=INFO source=app.go:323 msg="shutting down desktop server"
time=2025-10-19T12:57:50.881+02:00 level=INFO source=app.go:328 msg="shutting down ollama server"
time=2025-10-19T12:57:55.888+02:00 level=WARN source=server.go:132 msg="timeout waiting for graceful shutdown; killing" pid=3832

<!-- gh-comment-id:3419565084 --> @Panican-Whyasker commented on GitHub (Oct 19, 2025): Same issue here. Ollama 0.12.6 on Windows 11, GPU nVidia GeForce 840M (CUDA compute capability 5.0, the minimum required by Ollama) with 2 GB of VRAM; CPU Intel Core i7-5600, 6 GB system RAM. Therefore, have tried only rather small LLMs like gemma3:270m and qwen3:1.7b. Trying to start the LLMs in either PowerShell or inside Ollama's GUI - same result: The model start takes forever. At the same time, one ollama.exe process keeps running at 25% CPU (which is one of four logical cores running at 100%). Looked at the process' threads with SysInternals Process Explorer, see attached screenshot. ![Image](https://github.com/user-attachments/assets/5b0169d4-e4ad-4755-8965-32d789b84505) Here is my server log: time=2025-10-19T12:39:08.441+02:00 level=INFO source=routes.go:1511 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\\Users\\Joro\\.ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]" time=2025-10-19T12:39:08.447+02:00 level=INFO source=images.go:522 msg="total blobs: 12" time=2025-10-19T12:39:08.447+02:00 level=INFO source=images.go:529 msg="total unused blobs removed: 0" time=2025-10-19T12:39:08.450+02:00 level=INFO source=routes.go:1564 msg="Listening on 127.0.0.1:11434 (version 0.12.6)" time=2025-10-19T12:39:08.453+02:00 level=INFO source=runner.go:80 msg="discovering available GPUs..." time=2025-10-19T12:39:10.284+02:00 level=INFO source=types.go:112 msg="inference compute" id=GPU-838173db-880d-6d37-e6ad-d4b277cdde5a library=CUDA compute=5.0 name=CUDA0 description="NVIDIA GeForce 840M" libdirs=ollama,cuda_v12 driver=13.0 pci_id=03:00.0 type=discrete total="2.0 GiB" available="2.0 GiB" time=2025-10-19T12:39:10.285+02:00 level=INFO source=routes.go:1605 msg="entering low vram mode" "total vram"="2.0 GiB" threshold="20.0 GiB" [GIN] 2025/10/19 - 12:39:10 | 200 | 522.6µs | 127.0.0.1 | HEAD "/" [GIN] 2025/10/19 - 12:39:10 | 200 | 3.7394ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/10/19 - 12:43:09 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2025/10/19 - 12:43:09 | 200 | 117.6405ms | 127.0.0.1 | POST "/api/show" And that's it. Ollama.exe (one of two copies in memory) keeps running at 25% CPU (100% of one logical core). ![Image](https://github.com/user-attachments/assets/bc9fa550-1bc7-4980-a5ad-86cc8280aa7e) When trying to run the same model from within Ollama's GUI, the server log gets a few extra lines: time=2025-10-19T12:54:34.628+02:00 level=INFO source=routes.go:1511 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\\Users\\Joro\\.ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]" time=2025-10-19T12:54:34.643+02:00 level=INFO source=images.go:522 msg="total blobs: 12" time=2025-10-19T12:54:34.657+02:00 level=INFO source=images.go:529 msg="total unused blobs removed: 0" time=2025-10-19T12:54:34.673+02:00 level=INFO source=routes.go:1564 msg="Listening on 127.0.0.1:11434 (version 0.12.6)" time=2025-10-19T12:54:34.675+02:00 level=INFO source=runner.go:80 msg="discovering available GPUs..." time=2025-10-19T12:54:37.090+02:00 level=INFO source=types.go:112 msg="inference compute" id=GPU-838173db-880d-6d37-e6ad-d4b277cdde5a library=CUDA compute=5.0 name=CUDA0 description="NVIDIA GeForce 840M" libdirs=ollama,cuda_v12 driver=13.0 pci_id=03:00.0 type=discrete total="2.0 GiB" available="2.0 GiB" time=2025-10-19T12:54:37.091+02:00 level=INFO source=routes.go:1605 msg="entering low vram mode" "total vram"="2.0 GiB" threshold="20.0 GiB" [GIN] 2025/10/19 - 12:54:37 | 200 | 525.5µs | 127.0.0.1 | GET "/api/version" [GIN] 2025/10/19 - 12:54:37 | 200 | 525.5µs | 127.0.0.1 | GET "/api/version" [GIN] 2025/10/19 - 12:54:37 | 200 | 5.7471ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/10/19 - 12:54:37 | 200 | 160.8987ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/10/19 - 12:54:44 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2025/10/19 - 12:54:44 | 200 | 6.6484ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/10/19 - 12:54:56 | 200 | 124.4086ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/10/19 - 12:54:56 | 200 | 100.1837ms | 127.0.0.1 | POST "/api/show" ![Image](https://github.com/user-attachments/assets/f7d385c1-46a3-4d49-a109-ccab9ad87632) And here's my app.log: time=2025-10-19T12:54:32.717+02:00 level=INFO source=app_windows.go:272 msg="starting Ollama" app=C:\Users\Joro\AppData\Local\Programs\Ollama version=0.12.6 OS=Windows/10.0.26100 time=2025-10-19T12:54:32.721+02:00 level=INFO source=app.go:232 msg="initialized tools registry" tool_count=0 time=2025-10-19T12:54:32.735+02:00 level=INFO source=app.go:247 msg="starting ollama server" time=2025-10-19T12:54:33.173+02:00 level=INFO source=app.go:279 msg="starting ui server" port=56109 time=2025-10-19T12:54:35.437+02:00 level=INFO source=ui.go:171 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=997.1µs request_id=1760871275436712400 version=0.12.6 time=2025-10-19T12:54:35.471+02:00 level=INFO source=ui.go:171 msg=site.serveHTTP http.method=GET http.path=/api/v1/chats http.pattern="GET /api/v1/chats" http.status=200 http.d=1.0016ms request_id=1760871275470420900 version=0.12.6 time=2025-10-19T12:54:35.490+02:00 level=INFO source=ui.go:171 msg=site.serveHTTP http.method=GET http.path=/api/v1/me http.pattern="GET /api/v1/me" http.status=200 http.d=121.4562ms request_id=1760871275368774800 version=0.12.6 time=2025-10-19T12:54:36.039+02:00 level=ERROR source=ui.go:1617 msg="failed to get inference compute" error="timeout scanning server log for inference compute details" time=2025-10-19T12:54:36.039+02:00 level=ERROR source=ui.go:171 msg=site.serveHTTP error="failed to get inference compute: timeout scanning server log for inference compute details" http.method=GET http.path=/api/v1/inference-compute http.pattern="GET /api/v1/inference-compute" http.status=500 http.d=592.3808ms request_id=1760871275447595400 version=0.12.6 time=2025-10-19T12:54:36.174+02:00 level=INFO source=updater.go:252 msg="beginning update checker" interval=1h0m0s time=2025-10-19T12:54:37.091+02:00 level=INFO source=ui.go:171 msg=site.serveHTTP http.method=GET http.path=/api/v1/health http.pattern="GET /api/v1/health" http.status=200 http.d=1.6225602s request_id=1760871275469340400 version=0.12.6 time=2025-10-19T12:54:37.098+02:00 level=INFO source=ui.go:171 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=1.6539439s request_id=1760871275444706100 version=0.12.6 time=2025-10-19T12:54:37.187+02:00 level=INFO source=server.go:343 msg=Matched "inference compute"="{Library:CUDA Variant: Compute:5.0 Driver:13.0 Name:CUDA0 VRAM:2.0 GiB}" time=2025-10-19T12:54:37.187+02:00 level=INFO source=ui.go:171 msg=site.serveHTTP http.method=GET http.path=/api/v1/inference-compute http.pattern="GET /api/v1/inference-compute" http.status=200 http.d=128.9369ms request_id=1760871277058569100 version=0.12.6 time=2025-10-19T12:54:37.253+02:00 level=INFO source=ui.go:171 msg=site.serveHTTP http.method=GET http.path=/api/v1/model/gemma3:270m/capabilities http.pattern="GET /api/v1/model/{model}/capabilities" http.status=200 http.d=1.7391883s request_id=1760871275514116200 version=0.12.6 time=2025-10-19T12:54:37.293+02:00 level=INFO source=ui.go:171 msg=site.serveHTTP http.method=POST http.path=/api/v1/model/upstream http.pattern="POST /api/v1/model/upstream" http.status=200 http.d=161.3473ms request_id=1760871277131674100 version=0.12.6 time=2025-10-19T12:54:40.146+02:00 level=INFO source=ui.go:171 msg=site.serveHTTP http.method=GET http.path=/api/v1/chat/0199fbf4-fbea-7735-85af-904746282010 http.pattern="GET /api/v1/chat/{id}" http.status=200 http.d=15.5374ms request_id=1760871280131187300 version=0.12.6 time=2025-10-19T12:54:42.095+02:00 level=INFO source=ui.go:171 msg=site.serveHTTP http.method=GET http.path=/api/v1/chat/0199fbf4-fbea-7735-85af-904746282010 http.pattern="GET /api/v1/chat/{id}" http.status=200 http.d=507.5µs request_id=1760871282095350400 version=0.12.6 time=2025-10-19T12:54:44.635+02:00 level=INFO source=ui.go:171 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=950.6µs request_id=1760871284634242300 version=0.12.6 time=2025-10-19T12:54:44.639+02:00 level=INFO source=ui.go:171 msg=site.serveHTTP http.method=GET http.path=/api/v1/chat/0199fbf4-fbea-7735-85af-904746282010 http.pattern="GET /api/v1/chat/{id}" http.status=200 http.d=1.9311ms request_id=1760871284637210500 version=0.12.6 time=2025-10-19T12:54:44.646+02:00 level=INFO source=ui.go:171 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=10.3327ms request_id=1760871284636351800 version=0.12.6 time=2025-10-19T12:57:50.812+02:00 level=ERROR source=ui.go:1178 msg="chat stream error" error="Post \"http://127.0.0.1:11434/api/chat\": context canceled" time=2025-10-19T12:57:50.814+02:00 level=INFO source=ui.go:171 msg=site.serveHTTP http.method=POST http.path=/api/v1/chat/0199fbf4-fbea-7735-85af-904746282010 http.pattern="POST /api/v1/chat/{id}" http.status=200 http.d=2m54.1014868s request_id=1760871296712971700 version=0.12.6 time=2025-10-19T12:57:50.878+02:00 level=INFO source=app.go:323 msg="shutting down desktop server" time=2025-10-19T12:57:50.881+02:00 level=INFO source=app.go:328 msg="shutting down ollama server" time=2025-10-19T12:57:55.888+02:00 level=WARN source=server.go:132 msg="timeout waiting for graceful shutdown; killing" pid=3832
GiteaMirror commented 2026-04-22 17:28:28 -05:00
Author
Owner
Copy Link

@Panican-Whyasker commented on GitHub (Oct 19, 2025):

Regarding my earlier comment: That was with a new Ollama installation, on a freshly installed (and updated) Windows 11.

My main laptop with Ollama 0.12.6 (also Windows 11; Intel Core i9-9880H; nVidia Quadro RTX3000 w. 6 GB of VRAM; 128 GB of system RAM) runs normally the above LLMs. Here, Ollama was updated to v.0.12.6 shortly after that update became available.

<!-- gh-comment-id:3419607773 --> @Panican-Whyasker commented on GitHub (Oct 19, 2025): Regarding my earlier comment: That was with a new Ollama installation, on a freshly installed (and updated) Windows 11. My main laptop with Ollama 0.12.6 (also Windows 11; Intel Core i9-9880H; nVidia Quadro RTX3000 w. 6 GB of VRAM; 128 GB of system RAM) runs normally the above LLMs. Here, Ollama was updated to v.0.12.6 shortly after that update became available.
GiteaMirror commented 2026-04-22 17:28:28 -05:00
Author
Owner
Copy Link

@Panican-Whyasker commented on GitHub (Oct 19, 2025):

Update: The issue is not present in Ollama v.0.12.3. However, updating to 0.12.6 breaks it.

@samialisayed you may want to download and install version 0.12.3 (it will replace v.0.12.6, just don't apply the update to 0.12.6, Ollama downloads and offers it very soon).

(https://github.com/ollama/ollama/releases)

(https://github.com/ollama/ollama/releases/download/v0.12.3/OllamaSetup.exe)

Image

Image

Image

<!-- gh-comment-id:3419646824 --> @Panican-Whyasker commented on GitHub (Oct 19, 2025): Update: The issue is not present in Ollama v.0.12.3. However, updating to 0.12.6 breaks it. @samialisayed you may want to download and install version 0.12.3 (it will replace v.0.12.6, just don't apply the update to 0.12.6, Ollama downloads and offers it very soon). (https://github.com/ollama/ollama/releases) (https://github.com/ollama/ollama/releases/download/v0.12.3/OllamaSetup.exe) ![Image](https://github.com/user-attachments/assets/a50475f8-cf08-4853-a5f8-646832a997ca) ![Image](https://github.com/user-attachments/assets/38d194ce-2bf1-4c94-9923-00d01ebc2811) ![Image](https://github.com/user-attachments/assets/361ff374-35bd-4730-9fd0-946627238c96)
GiteaMirror commented 2026-04-22 17:28:28 -05:00
Author
Owner
Copy Link

@Panican-Whyasker commented on GitHub (Oct 20, 2025):

@samialisayed: as @rick-github explained in (https://github.com/ollama/ollama/issues/12699), ollama 0.12.3 is not affected; the issue likely starts with 0.12.4.

<!-- gh-comment-id:3421734212 --> @Panican-Whyasker commented on GitHub (Oct 20, 2025): @samialisayed: as @rick-github explained in (https://github.com/ollama/ollama/issues/12699), ollama 0.12.3 is not affected; the issue likely starts with 0.12.4.
GiteaMirror commented 2026-04-22 17:28:29 -05:00
Author
Owner
Copy Link

@Panican-Whyasker commented on GitHub (Oct 20, 2025):

Interestingly, no problem with ollama 0.12.6 on Windows Server 2016 Datacenter (GPU-less):

Image

<!-- gh-comment-id:3421787124 --> @Panican-Whyasker commented on GitHub (Oct 20, 2025): Interestingly, no problem with ollama 0.12.6 on Windows Server 2016 Datacenter (GPU-less): ![Image](https://github.com/user-attachments/assets/d4778c6c-a176-4fc5-b749-2e4226296b79)
GiteaMirror commented 2026-04-22 17:28:30 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 20, 2025):

Thanks for the data point. Based on the initial reports I thought it was due to the lack of GPU, and not widely reported because most users have a GPU. But it seems like there is something else at play.

<!-- gh-comment-id:3421970748 --> @rick-github commented on GitHub (Oct 20, 2025): Thanks for the data point. Based on the initial reports I thought it was due to the lack of GPU, and not widely reported because most users have a GPU. But it seems like there is something else at play.
GiteaMirror commented 2026-04-22 17:28:31 -05:00
Author
Owner
Copy Link

@samialisayed commented on GitHub (Oct 22, 2025):

@Panican-Whyasker I have installed the lower version and it works. thank you

<!-- gh-comment-id:3432485556 --> @samialisayed commented on GitHub (Oct 22, 2025): @Panican-Whyasker I have installed the lower version and it works. thank you
GiteaMirror commented 2026-04-22 17:28:32 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Oct 29, 2025):

Please give 0.12.7 a try and let us know if the issues are resolved. If not, please share an updated log with OLLAMA_DEBUG=2 set so we can take a look.

<!-- gh-comment-id:3464657681 --> @dhiltgen commented on GitHub (Oct 29, 2025): Please give 0.12.7 a try and let us know if the issues are resolved. If not, please share an updated log with OLLAMA_DEBUG=2 set so we can take a look.
GiteaMirror commented 2026-04-22 17:28:34 -05:00
Author
Owner
Copy Link

@katmandoo212 commented on GitHub (Oct 30, 2025):

I gave 0.12.7 a try. with OLLAMA_DEBUG=2. I could not get local models to load, but cloud models do work. gpt-oss:20b-cloud for example. This is my server.log followed by my app.log. I hope this helps.

time=2025-10-29T21:44:11.691-04:00 level=INFO source=routes.go:1524 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:16384 OLLAMA_DEBUG:DEBUG-4 OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:G:\OllamaFiles\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]"
time=2025-10-29T21:44:11.745-04:00 level=INFO source=images.go:522 msg="total blobs: 349"
time=2025-10-29T21:44:11.776-04:00 level=INFO source=images.go:529 msg="total unused blobs removed: 0"
time=2025-10-29T21:44:11.786-04:00 level=INFO source=routes.go:1577 msg="Listening on 127.0.0.1:11434 (version 0.12.7)"
time=2025-10-29T21:44:11.786-04:00 level=DEBUG source=sched.go:120 msg="starting llm scheduler"
time=2025-10-29T21:44:11.788-04:00 level=INFO source=runner.go:76 msg="discovering available GPUs..."
time=2025-10-29T21:44:11.788-04:00 level=TRACE source=runner.go:471 msg="starting runner for device discovery" libDirs="[C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12]" extraEnvs=map[]
time=2025-10-29T21:44:11.801-04:00 level=INFO source=server.go:385 msg="starting runner" cmd="C:\Users\User\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 60946"
time=2025-10-29T21:44:11.802-04:00 level=DEBUG source=server.go:386 msg=subprocess OLLAMA_MODELS=G:\OllamaFiles\models OLLAMA_DEBUG=2 OLLAMA_CONTEXT_LENGTH=16384 OLLAMA_AUTO_UPDATE=false OLLAMA_RAGTEMP=C:\OllamaRAGTemp PATH="C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12;C:\Program Files\PowerShell\7;C:\Program Files (x86)\oh-my-posh\bin\;C:\Users\User\Downloads\vcmake\vcpkg\installed\x64_windows;C:\Program Files\Common Files\Oracle\Java\javapath;C:\ActiveTcl\bin;C:\Program Files\Microsoft MPI\Bin\;C:\Users\User\AppData\Local\Programs\Python\Python314\Scripts;C:\Users\User\AppData\Local\Programs\Python\Python314;C:\Users\User\AppData\Local\Programs\Python\Python314\tct\tcl8.6;C:\Users\User\AppData\Local\Programs\Python\Python314\tcl;C:\Users\User\AppData\Local\Programs\Python\Python313\Scripts;C:\Users\User\AppData\Local\Programs\Python\Python313;C:\Users\User\AppData\Local\Programs\Python\Python313\tcl\tcl8.6;C:\Users\User\AppData\Local\Programs\Python\Python313\tcl;C:\Program Files\OpenSSL\bin;C:\Users\User\AppData\Roaming\ActiveState\bin;C:\Windows\system32;C:\Windows;C:\Windows\System32\Wbem;C:\Windows\System32\WindowsPowerShell\v1.0\;C:\Program Files\Graphviz\bin;C:\Windows\System32\OpenSSH\;C:\Program Files\Microsoft SQL Server\130\Tools\Binn\;C:\Program Files\Microsoft SQL Server\Client SDK\ODBC\170\Tools\Binn\;C:\Program Files\dotnet\;C:\Program Files\Microsoft SQL Server\150\Tools\Binn\;C:\Program Files (x86)\Microsoft SQL Server\150\DTS\Binn\;C:\Program Files\Microsoft SQL Server\150\DTS\Binn\;C:\Program Files (x86)\Microsoft SQL Server\150\Tools\Binn\;C:\Program Files\Azure Data Studio\bin;C:\WINDOWS\system32;C:\WINDOWS;C:\WINDOWS\System32\Wbem;C:\WINDOWS\System32\WindowsPowerShell\v1.0\;C:\WINDOWS\System32\OpenSSH\;C:\ProgramData\chocolatey\bin;C:\Program Files\Java\jdk-21\bin;C:\Program Files\NASM;C:\Program Files\Microsoft VS Code\bin;C:\Program Files\gs\gs10.03.0\bin;C:\Program Files (x86)\Microsoft SQL Server\160\DTS\Binn\;C:\Program Files\PuTTY\;C:\Program Files\RedHat\Podman\;C:\TDM-GCC-64\bin;D:\home\blt\github\vcpkg;C:\Program Files\CMake\bin;C:\Program Files\nodejs\;C:\Program Files\Go\bin;C:\Program Files\Pandoc\;C:\Program Files\Docker\Docker\resources\bin;C:\Program Files\PowerShell\7\;C:\Program Files (x86)\Windows Kits\10\Windows Performance Toolkit\;C:\Program Files\Git\cmd;C:\Users\User\AppData\Local\Programs\oh-my-posh\bin\;C:\Users\User\.local\bin;C:\Users\User\AppData\Local\Programs\Ollama;C:\Users\User\Downloads\vcmake\vcpkg\installed\x64_windows;C:\Users\User\.cargo\bin;C:\Program Files\OpenSSL\bin;C:\Users\User\AppData\Local\Microsoft\WindowsApps;C:\Program Files\Azure Data Studio\bin;C:\Program Files\PostgreSQL\15\bin;C:\Users\User\AppData\Local\GitHubDesktop\bin;C:\Users\User\Downloads\ffmpeg-master-latest-win64-gpl\ffmpeg-master-latest-win64-gpl\bin;C:\Program Files\Graphviz\bin;c:\Program Files\zig;c:\users\user\.local\bin;C:\Program Files (x86)\Intel\oneAPI;C:\Users\User\go\bin;C:\Users\User\.lmstudio\bin;C:\Users\User\.dotnet\tools;C:\Users\User\AppData\Local\Programs\Windsurf\bin;C:\Users\User\AppData\Local\reflex\bun\bin;C:\Users\User\AppData\Local\Programs\MiKTeX\miktex\bin\x64\;C:\Users\User\AppData\Roaming\npm;C:\Users\User\go\bin;C:\Users\User\AppData\Local\PowerToys\" OLLAMA_LIBRARY_PATH=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12
time=2025-10-29T21:44:11.867-04:00 level=INFO source=runner.go:1337 msg="starting ollama engine"
time=2025-10-29T21:44:11.868-04:00 level=INFO source=runner.go:1372 msg="Server listening on 127.0.0.1:60946"
time=2025-10-29T21:44:11.879-04:00 level=DEBUG source=gguf.go:590 msg=general.architecture type=string
time=2025-10-29T21:44:11.879-04:00 level=DEBUG source=gguf.go:590 msg=tokenizer.ggml.model type=string
time=2025-10-29T21:44:11.879-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32
time=2025-10-29T21:44:11.880-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32
time=2025-10-29T21:44:11.881-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.file_type default=0
time=2025-10-29T21:44:11.881-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.name default=""
time=2025-10-29T21:44:11.881-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.description default=""
time=2025-10-29T21:44:11.881-04:00 level=INFO source=ggml.go:135 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
time=2025-10-29T21:44:11.881-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama
load_backend: loaded CPU backend from C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll
time=2025-10-29T21:44:11.913-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12
dl_load_library unable to load library C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll: The specified module could not be found.

time=2025-10-29T21:44:12.094-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(clang)
time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.block_count default=0
time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.pooling_type default=0
time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.expert_count default=0
time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}"
time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}"
time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}"
time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}"
time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true
time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false
time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0
time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}"
time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.pre default=""
time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.block_count default=0
time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.embedding_length default=0
time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.head_count default=0
time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.head_count_kv default=0
time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.key_length default=0
time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.rope.dimension_count default=0
time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0
time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.rope.freq_base default=100000
time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.rope.scaling.factor default=1
time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=runner.go:1312 msg="dummy model load took" duration=216.4957ms
time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=runner.go:1317 msg="gathering device infos took" duration=0s
time=2025-10-29T21:44:12.096-04:00 level=TRACE source=runner.go:498 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12]" devices=[]
time=2025-10-29T21:44:12.096-04:00 level=DEBUG source=runner.go:468 msg="bootstrap discovery took" duration=308.1172ms OLLAMA_LIBRARY_PATH="[C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12]" extra_envs=map[]
time=2025-10-29T21:44:12.096-04:00 level=TRACE source=runner.go:471 msg="starting runner for device discovery" libDirs="[C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13]" extraEnvs=map[]
time=2025-10-29T21:44:12.099-04:00 level=INFO source=server.go:385 msg="starting runner" cmd="C:\Users\User\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 60955"
time=2025-10-29T21:44:12.099-04:00 level=DEBUG source=server.go:386 msg=subprocess OLLAMA_MODELS=G:\OllamaFiles\models OLLAMA_DEBUG=2 OLLAMA_CONTEXT_LENGTH=16384 OLLAMA_AUTO_UPDATE=false OLLAMA_RAGTEMP=C:\OllamaRAGTemp PATH="C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13;C:\Program Files\PowerShell\7;C:\Program Files (x86)\oh-my-posh\bin\;C:\Users\User\Downloads\vcmake\vcpkg\installed\x64_windows;C:\Program Files\Common Files\Oracle\Java\javapath;C:\ActiveTcl\bin;C:\Program Files\Microsoft MPI\Bin\;C:\Users\User\AppData\Local\Programs\Python\Python314\Scripts;C:\Users\User\AppData\Local\Programs\Python\Python314;C:\Users\User\AppData\Local\Programs\Python\Python314\tct\tcl8.6;C:\Users\User\AppData\Local\Programs\Python\Python314\tcl;C:\Users\User\AppData\Local\Programs\Python\Python313\Scripts;C:\Users\User\AppData\Local\Programs\Python\Python313;C:\Users\User\AppData\Local\Programs\Python\Python313\tcl\tcl8.6;C:\Users\User\AppData\Local\Programs\Python\Python313\tcl;C:\Program Files\OpenSSL\bin;C:\Users\User\AppData\Roaming\ActiveState\bin;C:\Windows\system32;C:\Windows;C:\Windows\System32\Wbem;C:\Windows\System32\WindowsPowerShell\v1.0\;C:\Program Files\Graphviz\bin;C:\Windows\System32\OpenSSH\;C:\Program Files\Microsoft SQL Server\130\Tools\Binn\;C:\Program Files\Microsoft SQL Server\Client SDK\ODBC\170\Tools\Binn\;C:\Program Files\dotnet\;C:\Program Files\Microsoft SQL Server\150\Tools\Binn\;C:\Program Files (x86)\Microsoft SQL Server\150\DTS\Binn\;C:\Program Files\Microsoft SQL Server\150\DTS\Binn\;C:\Program Files (x86)\Microsoft SQL Server\150\Tools\Binn\;C:\Program Files\Azure Data Studio\bin;C:\WINDOWS\system32;C:\WINDOWS;C:\WINDOWS\System32\Wbem;C:\WINDOWS\System32\WindowsPowerShell\v1.0\;C:\WINDOWS\System32\OpenSSH\;C:\ProgramData\chocolatey\bin;C:\Program Files\Java\jdk-21\bin;C:\Program Files\NASM;C:\Program Files\Microsoft VS Code\bin;C:\Program Files\gs\gs10.03.0\bin;C:\Program Files (x86)\Microsoft SQL Server\160\DTS\Binn\;C:\Program Files\PuTTY\;C:\Program Files\RedHat\Podman\;C:\TDM-GCC-64\bin;D:\home\blt\github\vcpkg;C:\Program Files\CMake\bin;C:\Program Files\nodejs\;C:\Program Files\Go\bin;C:\Program Files\Pandoc\;C:\Program Files\Docker\Docker\resources\bin;C:\Program Files\PowerShell\7\;C:\Program Files (x86)\Windows Kits\10\Windows Performance Toolkit\;C:\Program Files\Git\cmd;C:\Users\User\AppData\Local\Programs\oh-my-posh\bin\;C:\Users\User\.local\bin;C:\Users\User\AppData\Local\Programs\Ollama;C:\Users\User\Downloads\vcmake\vcpkg\installed\x64_windows;C:\Users\User\.cargo\bin;C:\Program Files\OpenSSL\bin;C:\Users\User\AppData\Local\Microsoft\WindowsApps;C:\Program Files\Azure Data Studio\bin;C:\Program Files\PostgreSQL\15\bin;C:\Users\User\AppData\Local\GitHubDesktop\bin;C:\Users\User\Downloads\ffmpeg-master-latest-win64-gpl\ffmpeg-master-latest-win64-gpl\bin;C:\Program Files\Graphviz\bin;c:\Program Files\zig;c:\users\user\.local\bin;C:\Program Files (x86)\Intel\oneAPI;C:\Users\User\go\bin;C:\Users\User\.lmstudio\bin;C:\Users\User\.dotnet\tools;C:\Users\User\AppData\Local\Programs\Windsurf\bin;C:\Users\User\AppData\Local\reflex\bun\bin;C:\Users\User\AppData\Local\Programs\MiKTeX\miktex\bin\x64\;C:\Users\User\AppData\Roaming\npm;C:\Users\User\go\bin;C:\Users\User\AppData\Local\PowerToys\" OLLAMA_LIBRARY_PATH=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13
time=2025-10-29T21:44:12.161-04:00 level=INFO source=runner.go:1337 msg="starting ollama engine"
time=2025-10-29T21:44:12.162-04:00 level=INFO source=runner.go:1372 msg="Server listening on 127.0.0.1:60955"
time=2025-10-29T21:44:12.166-04:00 level=DEBUG source=gguf.go:590 msg=general.architecture type=string
time=2025-10-29T21:44:12.166-04:00 level=DEBUG source=gguf.go:590 msg=tokenizer.ggml.model type=string
time=2025-10-29T21:44:12.167-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32
time=2025-10-29T21:44:12.168-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32
time=2025-10-29T21:44:12.168-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.file_type default=0
time=2025-10-29T21:44:12.168-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.name default=""
time=2025-10-29T21:44:12.168-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.description default=""
time=2025-10-29T21:44:12.169-04:00 level=INFO source=ggml.go:135 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
time=2025-10-29T21:44:12.169-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama
load_backend: loaded CPU backend from C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll
time=2025-10-29T21:44:12.197-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13
ggml_cuda_init: failed to initialize CUDA: (null)
load_backend: loaded CUDA backend from C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13\ggml-cuda.dll
time=2025-10-29T21:44:12.283-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(clang)
time=2025-10-29T21:44:12.284-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.block_count default=0
time=2025-10-29T21:44:12.284-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.pooling_type default=0
time=2025-10-29T21:44:12.284-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.expert_count default=0
time=2025-10-29T21:44:12.284-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}"
time=2025-10-29T21:44:12.284-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}"
time=2025-10-29T21:44:12.284-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}"
time=2025-10-29T21:44:12.284-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}"
time=2025-10-29T21:44:12.284-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true
time=2025-10-29T21:44:12.284-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
time=2025-10-29T21:44:12.284-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false
time=2025-10-29T21:44:12.284-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0
time=2025-10-29T21:44:12.284-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}"
time=2025-10-29T21:44:12.284-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.pre default=""
time=2025-10-29T21:44:12.285-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.block_count default=0
time=2025-10-29T21:44:12.285-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.embedding_length default=0
time=2025-10-29T21:44:12.285-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.head_count default=0
time=2025-10-29T21:44:12.285-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.head_count_kv default=0
time=2025-10-29T21:44:12.285-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.key_length default=0
time=2025-10-29T21:44:12.285-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.rope.dimension_count default=0
time=2025-10-29T21:44:12.285-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0
time=2025-10-29T21:44:12.285-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.rope.freq_base default=100000
time=2025-10-29T21:44:12.285-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.rope.scaling.factor default=1
time=2025-10-29T21:44:12.285-04:00 level=DEBUG source=runner.go:1312 msg="dummy model load took" duration=119.2606ms
time=2025-10-29T21:44:12.285-04:00 level=DEBUG source=runner.go:1317 msg="gathering device infos took" duration=0s
time=2025-10-29T21:44:12.285-04:00 level=TRACE source=runner.go:498 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13]" devices=[]
time=2025-10-29T21:44:12.286-04:00 level=DEBUG source=runner.go:468 msg="bootstrap discovery took" duration=189.4849ms OLLAMA_LIBRARY_PATH="[C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13]" extra_envs=map[]
time=2025-10-29T21:44:12.286-04:00 level=TRACE source=runner.go:471 msg="starting runner for device discovery" libDirs="[C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\rocm]" extraEnvs=map[]
time=2025-10-29T21:44:12.288-04:00 level=INFO source=server.go:385 msg="starting runner" cmd="C:\Users\User\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 60962"
time=2025-10-29T21:44:12.288-04:00 level=DEBUG source=server.go:386 msg=subprocess OLLAMA_MODELS=G:\OllamaFiles\models OLLAMA_DEBUG=2 OLLAMA_CONTEXT_LENGTH=16384 OLLAMA_AUTO_UPDATE=false OLLAMA_RAGTEMP=C:\OllamaRAGTemp PATH="C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\rocm;C:\Program Files\PowerShell\7;C:\Program Files (x86)\oh-my-posh\bin\;C:\Users\User\Downloads\vcmake\vcpkg\installed\x64_windows;C:\Program Files\Common Files\Oracle\Java\javapath;C:\ActiveTcl\bin;C:\Program Files\Microsoft MPI\Bin\;C:\Users\User\AppData\Local\Programs\Python\Python314\Scripts;C:\Users\User\AppData\Local\Programs\Python\Python314;C:\Users\User\AppData\Local\Programs\Python\Python314\tct\tcl8.6;C:\Users\User\AppData\Local\Programs\Python\Python314\tcl;C:\Users\User\AppData\Local\Programs\Python\Python313\Scripts;C:\Users\User\AppData\Local\Programs\Python\Python313;C:\Users\User\AppData\Local\Programs\Python\Python313\tcl\tcl8.6;C:\Users\User\AppData\Local\Programs\Python\Python313\tcl;C:\Program Files\OpenSSL\bin;C:\Users\User\AppData\Roaming\ActiveState\bin;C:\Windows\system32;C:\Windows;C:\Windows\System32\Wbem;C:\Windows\System32\WindowsPowerShell\v1.0\;C:\Program Files\Graphviz\bin;C:\Windows\System32\OpenSSH\;C:\Program Files\Microsoft SQL Server\130\Tools\Binn\;C:\Program Files\Microsoft SQL Server\Client SDK\ODBC\170\Tools\Binn\;C:\Program Files\dotnet\;C:\Program Files\Microsoft SQL Server\150\Tools\Binn\;C:\Program Files (x86)\Microsoft SQL Server\150\DTS\Binn\;C:\Program Files\Microsoft SQL Server\150\DTS\Binn\;C:\Program Files (x86)\Microsoft SQL Server\150\Tools\Binn\;C:\Program Files\Azure Data Studio\bin;C:\WINDOWS\system32;C:\WINDOWS;C:\WINDOWS\System32\Wbem;C:\WINDOWS\System32\WindowsPowerShell\v1.0\;C:\WINDOWS\System32\OpenSSH\;C:\ProgramData\chocolatey\bin;C:\Program Files\Java\jdk-21\bin;C:\Program Files\NASM;C:\Program Files\Microsoft VS Code\bin;C:\Program Files\gs\gs10.03.0\bin;C:\Program Files (x86)\Microsoft SQL Server\160\DTS\Binn\;C:\Program Files\PuTTY\;C:\Program Files\RedHat\Podman\;C:\TDM-GCC-64\bin;D:\home\blt\github\vcpkg;C:\Program Files\CMake\bin;C:\Program Files\nodejs\;C:\Program Files\Go\bin;C:\Program Files\Pandoc\;C:\Program Files\Docker\Docker\resources\bin;C:\Program Files\PowerShell\7\;C:\Program Files (x86)\Windows Kits\10\Windows Performance Toolkit\;C:\Program Files\Git\cmd;C:\Users\User\AppData\Local\Programs\oh-my-posh\bin\;C:\Users\User\.local\bin;C:\Users\User\AppData\Local\Programs\Ollama;C:\Users\User\Downloads\vcmake\vcpkg\installed\x64_windows;C:\Users\User\.cargo\bin;C:\Program Files\OpenSSL\bin;C:\Users\User\AppData\Local\Microsoft\WindowsApps;C:\Program Files\Azure Data Studio\bin;C:\Program Files\PostgreSQL\15\bin;C:\Users\User\AppData\Local\GitHubDesktop\bin;C:\Users\User\Downloads\ffmpeg-master-latest-win64-gpl\ffmpeg-master-latest-win64-gpl\bin;C:\Program Files\Graphviz\bin;c:\Program Files\zig;c:\users\user\.local\bin;C:\Program Files (x86)\Intel\oneAPI;C:\Users\User\go\bin;C:\Users\User\.lmstudio\bin;C:\Users\User\.dotnet\tools;C:\Users\User\AppData\Local\Programs\Windsurf\bin;C:\Users\User\AppData\Local\reflex\bun\bin;C:\Users\User\AppData\Local\Programs\MiKTeX\miktex\bin\x64\;C:\Users\User\AppData\Roaming\npm;C:\Users\User\go\bin;C:\Users\User\AppData\Local\PowerToys\" OLLAMA_LIBRARY_PATH=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\rocm
time=2025-10-29T21:44:12.364-04:00 level=INFO source=runner.go:1337 msg="starting ollama engine"
time=2025-10-29T21:44:12.366-04:00 level=INFO source=runner.go:1372 msg="Server listening on 127.0.0.1:60962"
time=2025-10-29T21:44:12.375-04:00 level=DEBUG source=gguf.go:590 msg=general.architecture type=string
time=2025-10-29T21:44:12.375-04:00 level=DEBUG source=gguf.go:590 msg=tokenizer.ggml.model type=string
time=2025-10-29T21:44:12.375-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32
time=2025-10-29T21:44:12.377-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32
time=2025-10-29T21:44:12.377-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.file_type default=0
time=2025-10-29T21:44:12.377-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.name default=""
time=2025-10-29T21:44:12.377-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.description default=""
time=2025-10-29T21:44:12.377-04:00 level=INFO source=ggml.go:135 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
time=2025-10-29T21:44:12.377-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama
load_backend: loaded CPU backend from C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll
time=2025-10-29T21:44:12.406-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\rocm
ggml_cuda_init: failed to initialize ROCm: no ROCm-capable device is detected
load_backend: loaded ROCm backend from C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\rocm\ggml-hip.dll
time=2025-10-29T21:44:12.446-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(clang)
time=2025-10-29T21:44:12.446-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.block_count default=0
time=2025-10-29T21:44:12.446-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.pooling_type default=0
time=2025-10-29T21:44:12.446-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.expert_count default=0
time=2025-10-29T21:44:12.446-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}"
time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}"
time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}"
time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}"
time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true
time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false
time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0
time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}"
time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.pre default=""
time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.block_count default=0
time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.embedding_length default=0
time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.head_count default=0
time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.head_count_kv default=0
time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.key_length default=0
time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.rope.dimension_count default=0
time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0
time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.rope.freq_base default=100000
time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.rope.scaling.factor default=1
time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=runner.go:1312 msg="dummy model load took" duration=72.7312ms
time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=runner.go:1317 msg="gathering device infos took" duration=0s
time=2025-10-29T21:44:12.448-04:00 level=TRACE source=runner.go:498 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\rocm]" devices=[]
time=2025-10-29T21:44:12.448-04:00 level=DEBUG source=runner.go:468 msg="bootstrap discovery took" duration=162.4718ms OLLAMA_LIBRARY_PATH="[C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\rocm]" extra_envs=map[]
time=2025-10-29T21:44:12.448-04:00 level=DEBUG source=runner.go:120 msg="evluating which if any devices to filter out" initial_count=0
time=2025-10-29T21:44:12.448-04:00 level=TRACE source=runner.go:179 msg="supported GPU library combinations before filtering" supported=map[]
time=2025-10-29T21:44:12.448-04:00 level=DEBUG source=runner.go:41 msg="GPU bootstrap discovery took" duration=661.722ms
time=2025-10-29T21:44:12.449-04:00 level=INFO source=types.go:60 msg="inference compute" id=cpu library=cpu compute="" name=cpu description=cpu libdirs=ollama driver="" pci_id="" type="" total="11.9 GiB" available="6.0 GiB"
time=2025-10-29T21:44:12.449-04:00 level=INFO source=routes.go:1618 msg="entering low vram mode" "total vram"="0 B" threshold="20.0 GiB"
[GIN] 2025/10/29 - 21:44:12 | 200 | 541µs | 127.0.0.1 | HEAD "/"
[GIN] 2025/10/29 - 21:44:12 | 200 | 57.0626ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2025/10/29 - 21:44:24 | 200 | 0s | 127.0.0.1 | GET "/api/version"
[GIN] 2025/10/29 - 21:44:24 | 200 | 0s | 127.0.0.1 | GET "/api/version"
[GIN] 2025/10/29 - 21:44:24 | 200 | 185.0917ms | 127.0.0.1 | GET "/api/tags"
time=2025-10-29T21:44:25.105-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32
[GIN] 2025/10/29 - 21:44:25 | 200 | 254.2493ms | 127.0.0.1 | POST "/api/show"
[GIN] 2025/10/29 - 21:44:40 | 200 | 0s | 127.0.0.1 | GET "/api/version"
time=2025-10-29T21:44:40.843-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32
[GIN] 2025/10/29 - 21:44:40 | 200 | 250.6383ms | 127.0.0.1 | POST "/api/show"
[GIN] 2025/10/29 - 21:44:40 | 200 | 106.9248ms | 127.0.0.1 | GET "/api/tags"
time=2025-10-29T21:44:41.009-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32
[GIN] 2025/10/29 - 21:44:41 | 200 | 166.299ms | 127.0.0.1 | POST "/api/show"
time=2025-10-29T21:44:41.196-04:00 level=DEBUG source=runner.go:267 msg="refreshing free memory"
time=2025-10-29T21:44:41.196-04:00 level=DEBUG source=runner.go:41 msg="overall device VRAM discovery took" duration=0s
[GIN] 2025/10/29 - 21:45:10 | 200 | 0s | 127.0.0.1 | GET "/api/version"
[GIN] 2025/10/29 - 21:45:11 | 200 | 78.7139ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2025/10/29 - 21:45:41 | 200 | 0s | 127.0.0.1 | GET "/api/version"
[GIN] 2025/10/29 - 21:45:41 | 200 | 52.8417ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2025/10/29 - 21:46:11 | 200 | 0s | 127.0.0.1 | GET "/api/version"
[GIN] 2025/10/29 - 21:46:11 | 200 | 74.5929ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2025/10/29 - 21:46:41 | 200 | 0s | 127.0.0.1 | GET "/api/version"
[GIN] 2025/10/29 - 21:46:41 | 200 | 199.5415ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2025/10/29 - 21:47:11 | 200 | 0s | 127.0.0.1 | GET "/api/version"
[GIN] 2025/10/29 - 21:47:11 | 200 | 70.797ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2025/10/29 - 21:47:14 | 200 | 31.5551ms | 127.0.0.1 | POST "/api/show"
[GIN] 2025/10/29 - 21:47:23 | 200 | 33.352ms | 127.0.0.1 | POST "/api/show"
[GIN] 2025/10/29 - 21:47:23 | 200 | 35.7424ms | 127.0.0.1 | POST "/api/show"
[GIN] 2025/10/29 - 21:47:25 | 200 | 1.3314975s | 127.0.0.1 | POST "/api/chat"
[GIN] 2025/10/29 - 21:47:27 | 200 | 814.5542ms | 127.0.0.1 | POST "/api/chat"
[GIN] 2025/10/29 - 21:47:28 | 200 | 1.1260067s | 127.0.0.1 | POST "/api/chat"
[GIN] 2025/10/29 - 21:47:30 | 200 | 1.6694057s | 127.0.0.1 | POST "/api/chat"
[GIN] 2025/10/29 - 21:47:41 | 200 | 0s | 127.0.0.1 | GET "/api/version"
[GIN] 2025/10/29 - 21:47:41 | 200 | 55.0317ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2025/10/29 - 21:48:11 | 200 | 0s | 127.0.0.1 | GET "/api/version"
[GIN] 2025/10/29 - 21:48:11 | 200 | 52.7654ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2025/10/29 - 21:48:41 | 200 | 0s | 127.0.0.1 | GET "/api/version"
[GIN] 2025/10/29 - 21:48:41 | 200 | 49.1216ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2025/10/29 - 21:49:11 | 200 | 0s | 127.0.0.1 | GET "/api/version"
[GIN] 2025/10/29 - 21:49:11 | 200 | 60.5865ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2025/10/29 - 21:49:41 | 200 | 0s | 127.0.0.1 | GET "/api/version"
[GIN] 2025/10/29 - 21:49:41 | 200 | 54.8271ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2025/10/29 - 21:50:11 | 200 | 0s | 127.0.0.1 | GET "/api/version"
[GIN] 2025/10/29 - 21:50:11 | 200 | 58.8494ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2025/10/29 - 21:50:42 | 200 | 0s | 127.0.0.1 | GET "/api/version"
[GIN] 2025/10/29 - 21:50:42 | 200 | 53.4373ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2025/10/29 - 21:51:12 | 200 | 0s | 127.0.0.1 | GET "/api/version"
[GIN] 2025/10/29 - 21:51:12 | 200 | 54.2343ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2025/10/29 - 21:51:42 | 200 | 0s | 127.0.0.1 | GET "/api/version"
[GIN] 2025/10/29 - 21:51:42 | 200 | 59.3495ms | 127.0.0.1 | GET "/api/tags"

time=2025-10-29T21:44:10.544-04:00 level=INFO source=app_windows.go:270 msg="starting Ollama" app=C:\Users\User\AppData\Local\Programs\Ollama version=0.12.7 OS=Windows/10.0.19045
time=2025-10-29T21:44:10.546-04:00 level=INFO source=app.go:231 msg="initialized tools registry" tool_count=0
time=2025-10-29T21:44:10.587-04:00 level=INFO source=app.go:246 msg="starting ollama server"
time=2025-10-29T21:44:10.931-04:00 level=INFO source=app.go:275 msg="starting ui server" port=60942
time=2025-10-29T21:44:10.953-04:00 level=INFO source=app.go:336 msg="deferring pending update for fast startup"
time=2025-10-29T21:44:13.931-04:00 level=INFO source=updater.go:252 msg="beginning update checker" interval=1h0m0s
time=2025-10-29T21:44:24.714-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=0s request_id=1761788664714383500 version=0.12.7
time=2025-10-29T21:44:24.719-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/me http.pattern="GET /api/v1/me" http.status=200 http.d=84.5648ms request_id=1761788664634994100 version=0.12.7
time=2025-10-29T21:44:24.733-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/health http.pattern="GET /api/v1/health" http.status=200 http.d=11.0824ms request_id=1761788664722425600 version=0.12.7
time=2025-10-29T21:44:24.749-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/chats http.pattern="GET /api/v1/chats" http.status=200 http.d=24.2975ms request_id=1761788664725422700 version=0.12.7
time=2025-10-29T21:44:24.762-04:00 level=INFO source=server.go:343 msg=Matched "inference compute"="{Library:cpu Variant: Compute: Driver: Name:cpu VRAM:11.9 GiB}"
time=2025-10-29T21:44:24.762-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/inference-compute http.pattern="GET /api/v1/inference-compute" http.status=200 http.d=43.6747ms request_id=1761788664718542400 version=0.12.7
time=2025-10-29T21:44:24.915-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=199.1878ms request_id=1761788664716368200 version=0.12.7
time=2025-10-29T21:44:24.984-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/chats http.pattern="GET /api/v1/chats" http.status=200 http.d=25.1705ms request_id=1761788664959127700 version=0.12.7
time=2025-10-29T21:44:25.117-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/model/qwen3:4b/capabilities http.pattern="GET /api/v1/model/{model}/capabilities" http.status=200 http.d=264.7715ms request_id=1761788664853051300 version=0.12.7
time=2025-10-29T21:44:25.399-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=POST http.path=/api/v1/model/upstream http.pattern="POST /api/v1/model/upstream" http.status=200 http.d=162.7553ms request_id=1761788665236699300 version=0.12.7
time=2025-10-29T21:44:40.658-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/chats http.pattern="GET /api/v1/chats" http.status=200 http.d=23.821ms request_id=1761788680635163500 version=0.12.7
time=2025-10-29T21:44:40.767-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=1.3556ms request_id=1761788680766282800 version=0.12.7
time=2025-10-29T21:44:40.878-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=111.7008ms request_id=1761788680767101300 version=0.12.7
time=2025-10-29T21:45:11.007-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=86.2728ms request_id=1761788710921244800 version=0.12.7
time=2025-10-29T21:45:41.072-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=58.9496ms request_id=1761788741013530600 version=0.12.7
time=2025-10-29T21:46:11.160-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=81.4457ms request_id=1761788771078929500 version=0.12.7
time=2025-10-29T21:46:41.391-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=212.4071ms request_id=1761788801178638100 version=0.12.7
time=2025-10-29T21:47:08.047-04:00 level=ERROR source=ui.go:1179 msg="chat stream error" error="Post "http://127.0.0.1:11434/api/chat": context canceled"
time=2025-10-29T21:47:08.047-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=POST http.path=/api/v1/chat/new http.pattern="POST /api/v1/chat/{id}" http.status=200 http.d=2m27.4542528s request_id=1761788680592933600 version=0.12.7
time=2025-10-29T21:47:11.535-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=79.1006ms request_id=1761788831456019700 version=0.12.7
time=2025-10-29T21:47:14.028-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=POST http.path=/api/v1/settings http.pattern="POST /api/v1/settings" http.status=200 http.d=594µs request_id=1761788834028069900 version=0.12.7
time=2025-10-29T21:47:14.035-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=0s request_id=1761788834035388500 version=0.12.7
time=2025-10-29T21:47:14.084-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/model/gpt-oss:20b-cloud/capabilities http.pattern="GET /api/v1/model/{model}/capabilities" http.status=200 http.d=31.9895ms request_id=1761788834052226600 version=0.12.7
time=2025-10-29T21:47:14.396-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=POST http.path=/api/v1/model/upstream http.pattern="POST /api/v1/model/upstream" http.status=200 http.d=351.1287ms request_id=1761788834045034700 version=0.12.7
time=2025-10-29T21:47:30.128-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=POST http.path=/api/v1/chat/019a32c9-d991-770c-882b-2ab0187daa95 http.pattern="POST /api/v1/chat/{id}" http.status=200 http.d=6.3121519s request_id=1761788843815980500 version=0.12.7
time=2025-10-29T21:47:30.138-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/chat/019a32c9-d991-770c-882b-2ab0187daa95 http.pattern="GET /api/v1/chat/{id}" http.status=200 http.d=9.1821ms request_id=1761788850129584200 version=0.12.7
time=2025-10-29T21:47:41.608-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=61.4188ms request_id=1761788861546597500 version=0.12.7
time=2025-10-29T21:48:11.680-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=58.3517ms request_id=1761788891622309800 version=0.12.7
time=2025-10-29T21:48:41.752-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=51.5636ms request_id=1761788921700600300 version=0.12.7
time=2025-10-29T21:49:11.828-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=66.4161ms request_id=1761788951762197100 version=0.12.7
time=2025-10-29T21:49:41.898-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=56.9438ms request_id=1761788981841884900 version=0.12.7
time=2025-10-29T21:50:11.983-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=65.2983ms request_id=1761789011918117000 version=0.12.7
time=2025-10-29T21:50:42.065-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=57.7472ms request_id=1761789042007958300 version=0.12.7
time=2025-10-29T21:51:12.137-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=56.72ms request_id=1761789072080460500 version=0.12.7
time=2025-10-29T21:51:42.216-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=63.3792ms request_id=1761789102152736300 version=0.12.7
time=2025-10-29T21:52:12.303-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=71.2135ms request_id=1761789132232153000 version=0.12.7
time=2025-10-29T21:52:42.392-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=65.8005ms request_id=1761789162327049800 version=0.12.7

<!-- gh-comment-id:3465809632 --> @katmandoo212 commented on GitHub (Oct 30, 2025): I gave 0.12.7 a try. with OLLAMA_DEBUG=2. I could not get local models to load, but cloud models do work. gpt-oss:20b-cloud for example. This is my server.log followed by my app.log. I hope this helps. time=2025-10-29T21:44:11.691-04:00 level=INFO source=routes.go:1524 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:16384 OLLAMA_DEBUG:DEBUG-4 OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:G:\\OllamaFiles\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]" time=2025-10-29T21:44:11.745-04:00 level=INFO source=images.go:522 msg="total blobs: 349" time=2025-10-29T21:44:11.776-04:00 level=INFO source=images.go:529 msg="total unused blobs removed: 0" time=2025-10-29T21:44:11.786-04:00 level=INFO source=routes.go:1577 msg="Listening on 127.0.0.1:11434 (version 0.12.7)" time=2025-10-29T21:44:11.786-04:00 level=DEBUG source=sched.go:120 msg="starting llm scheduler" time=2025-10-29T21:44:11.788-04:00 level=INFO source=runner.go:76 msg="discovering available GPUs..." time=2025-10-29T21:44:11.788-04:00 level=TRACE source=runner.go:471 msg="starting runner for device discovery" libDirs="[C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" extraEnvs=map[] time=2025-10-29T21:44:11.801-04:00 level=INFO source=server.go:385 msg="starting runner" cmd="C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60946" time=2025-10-29T21:44:11.802-04:00 level=DEBUG source=server.go:386 msg=subprocess OLLAMA_MODELS=G:\OllamaFiles\models OLLAMA_DEBUG=2 OLLAMA_CONTEXT_LENGTH=16384 OLLAMA_AUTO_UPDATE=false OLLAMA_RAGTEMP=C:\OllamaRAGTemp PATH="C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12;C:\\Program Files\\PowerShell\\7;C:\\Program Files (x86)\\oh-my-posh\\bin\\;C:\\Users\\User\\Downloads\\vcmake\\vcpkg\\installed\\x64_windows;C:\\Program Files\\Common Files\\Oracle\\Java\\javapath;C:\\ActiveTcl\\bin;C:\\Program Files\\Microsoft MPI\\Bin\\;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314\\Scripts;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314\\tct\\tcl8.6;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314\\tcl;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313\\Scripts;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313\\tcl\\tcl8.6;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313\\tcl;C:\\Program Files\\OpenSSL\\bin;C:\\Users\\User\\AppData\\Roaming\\ActiveState\\bin;C:\\Windows\\system32;C:\\Windows;C:\\Windows\\System32\\Wbem;C:\\Windows\\System32\\WindowsPowerShell\\v1.0\\;C:\\Program Files\\Graphviz\\bin;C:\\Windows\\System32\\OpenSSH\\;C:\\Program Files\\Microsoft SQL Server\\130\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\170\\Tools\\Binn\\;C:\\Program Files\\dotnet\\;C:\\Program Files\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\150\\DTS\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\150\\DTS\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files\\Azure Data Studio\\bin;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\ProgramData\\chocolatey\\bin;C:\\Program Files\\Java\\jdk-21\\bin;C:\\Program Files\\NASM;C:\\Program Files\\Microsoft VS Code\\bin;C:\\Program Files\\gs\\gs10.03.0\\bin;C:\\Program Files (x86)\\Microsoft SQL Server\\160\\DTS\\Binn\\;C:\\Program Files\\PuTTY\\;C:\\Program Files\\RedHat\\Podman\\;C:\\TDM-GCC-64\\bin;D:\\home\\blt\\github\\vcpkg;C:\\Program Files\\CMake\\bin;C:\\Program Files\\nodejs\\;C:\\Program Files\\Go\\bin;C:\\Program Files\\Pandoc\\;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\Program Files\\PowerShell\\7\\;C:\\Program Files (x86)\\Windows Kits\\10\\Windows Performance Toolkit\\;C:\\Program Files\\Git\\cmd;C:\\Users\\User\\AppData\\Local\\Programs\\oh-my-posh\\bin\\;C:\\Users\\User\\.local\\bin;C:\\Users\\User\\AppData\\Local\\Programs\\Ollama;C:\\Users\\User\\Downloads\\vcmake\\vcpkg\\installed\\x64_windows;C:\\Users\\User\\.cargo\\bin;C:\\Program Files\\OpenSSL\\bin;C:\\Users\\User\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Program Files\\Azure Data Studio\\bin;C:\\Program Files\\PostgreSQL\\15\\bin;C:\\Users\\User\\AppData\\Local\\GitHubDesktop\\bin;C:\\Users\\User\\Downloads\\ffmpeg-master-latest-win64-gpl\\ffmpeg-master-latest-win64-gpl\\bin;C:\\Program Files\\Graphviz\\bin;c:\\Program Files\\zig;c:\\users\\user\\.local\\bin;C:\\Program Files (x86)\\Intel\\oneAPI;C:\\Users\\User\\go\\bin;C:\\Users\\User\\.lmstudio\\bin;C:\\Users\\User\\.dotnet\\tools;C:\\Users\\User\\AppData\\Local\\Programs\\Windsurf\\bin;C:\\Users\\User\\AppData\\Local\\reflex\\bun\\bin;C:\\Users\\User\\AppData\\Local\\Programs\\MiKTeX\\miktex\\bin\\x64\\;C:\\Users\\User\\AppData\\Roaming\\npm;C:\\Users\\User\\go\\bin;C:\\Users\\User\\AppData\\Local\\PowerToys\\" OLLAMA_LIBRARY_PATH=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12 time=2025-10-29T21:44:11.867-04:00 level=INFO source=runner.go:1337 msg="starting ollama engine" time=2025-10-29T21:44:11.868-04:00 level=INFO source=runner.go:1372 msg="Server listening on 127.0.0.1:60946" time=2025-10-29T21:44:11.879-04:00 level=DEBUG source=gguf.go:590 msg=general.architecture type=string time=2025-10-29T21:44:11.879-04:00 level=DEBUG source=gguf.go:590 msg=tokenizer.ggml.model type=string time=2025-10-29T21:44:11.879-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32 time=2025-10-29T21:44:11.880-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32 time=2025-10-29T21:44:11.881-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.file_type default=0 time=2025-10-29T21:44:11.881-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.name default="" time=2025-10-29T21:44:11.881-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.description default="" time=2025-10-29T21:44:11.881-04:00 level=INFO source=ggml.go:135 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3 time=2025-10-29T21:44:11.881-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama load_backend: loaded CPU backend from C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll time=2025-10-29T21:44:11.913-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12 dl_load_library unable to load library C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll: The specified module could not be found. time=2025-10-29T21:44:12.094-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(clang) time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.block_count default=0 time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.pooling_type default=0 time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.expert_count default=0 time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}" time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}" time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}" time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}" time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0 time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0 time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}" time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.pre default="" time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.block_count default=0 time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.embedding_length default=0 time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.head_count default=0 time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.head_count_kv default=0 time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.key_length default=0 time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.rope.dimension_count default=0 time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0 time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.rope.freq_base default=100000 time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.rope.scaling.factor default=1 time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=runner.go:1312 msg="dummy model load took" duration=216.4957ms time=2025-10-29T21:44:12.094-04:00 level=DEBUG source=runner.go:1317 msg="gathering device infos took" duration=0s time=2025-10-29T21:44:12.096-04:00 level=TRACE source=runner.go:498 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" devices=[] time=2025-10-29T21:44:12.096-04:00 level=DEBUG source=runner.go:468 msg="bootstrap discovery took" duration=308.1172ms OLLAMA_LIBRARY_PATH="[C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" extra_envs=map[] time=2025-10-29T21:44:12.096-04:00 level=TRACE source=runner.go:471 msg="starting runner for device discovery" libDirs="[C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]" extraEnvs=map[] time=2025-10-29T21:44:12.099-04:00 level=INFO source=server.go:385 msg="starting runner" cmd="C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60955" time=2025-10-29T21:44:12.099-04:00 level=DEBUG source=server.go:386 msg=subprocess OLLAMA_MODELS=G:\OllamaFiles\models OLLAMA_DEBUG=2 OLLAMA_CONTEXT_LENGTH=16384 OLLAMA_AUTO_UPDATE=false OLLAMA_RAGTEMP=C:\OllamaRAGTemp PATH="C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13;C:\\Program Files\\PowerShell\\7;C:\\Program Files (x86)\\oh-my-posh\\bin\\;C:\\Users\\User\\Downloads\\vcmake\\vcpkg\\installed\\x64_windows;C:\\Program Files\\Common Files\\Oracle\\Java\\javapath;C:\\ActiveTcl\\bin;C:\\Program Files\\Microsoft MPI\\Bin\\;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314\\Scripts;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314\\tct\\tcl8.6;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314\\tcl;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313\\Scripts;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313\\tcl\\tcl8.6;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313\\tcl;C:\\Program Files\\OpenSSL\\bin;C:\\Users\\User\\AppData\\Roaming\\ActiveState\\bin;C:\\Windows\\system32;C:\\Windows;C:\\Windows\\System32\\Wbem;C:\\Windows\\System32\\WindowsPowerShell\\v1.0\\;C:\\Program Files\\Graphviz\\bin;C:\\Windows\\System32\\OpenSSH\\;C:\\Program Files\\Microsoft SQL Server\\130\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\170\\Tools\\Binn\\;C:\\Program Files\\dotnet\\;C:\\Program Files\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\150\\DTS\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\150\\DTS\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files\\Azure Data Studio\\bin;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\ProgramData\\chocolatey\\bin;C:\\Program Files\\Java\\jdk-21\\bin;C:\\Program Files\\NASM;C:\\Program Files\\Microsoft VS Code\\bin;C:\\Program Files\\gs\\gs10.03.0\\bin;C:\\Program Files (x86)\\Microsoft SQL Server\\160\\DTS\\Binn\\;C:\\Program Files\\PuTTY\\;C:\\Program Files\\RedHat\\Podman\\;C:\\TDM-GCC-64\\bin;D:\\home\\blt\\github\\vcpkg;C:\\Program Files\\CMake\\bin;C:\\Program Files\\nodejs\\;C:\\Program Files\\Go\\bin;C:\\Program Files\\Pandoc\\;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\Program Files\\PowerShell\\7\\;C:\\Program Files (x86)\\Windows Kits\\10\\Windows Performance Toolkit\\;C:\\Program Files\\Git\\cmd;C:\\Users\\User\\AppData\\Local\\Programs\\oh-my-posh\\bin\\;C:\\Users\\User\\.local\\bin;C:\\Users\\User\\AppData\\Local\\Programs\\Ollama;C:\\Users\\User\\Downloads\\vcmake\\vcpkg\\installed\\x64_windows;C:\\Users\\User\\.cargo\\bin;C:\\Program Files\\OpenSSL\\bin;C:\\Users\\User\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Program Files\\Azure Data Studio\\bin;C:\\Program Files\\PostgreSQL\\15\\bin;C:\\Users\\User\\AppData\\Local\\GitHubDesktop\\bin;C:\\Users\\User\\Downloads\\ffmpeg-master-latest-win64-gpl\\ffmpeg-master-latest-win64-gpl\\bin;C:\\Program Files\\Graphviz\\bin;c:\\Program Files\\zig;c:\\users\\user\\.local\\bin;C:\\Program Files (x86)\\Intel\\oneAPI;C:\\Users\\User\\go\\bin;C:\\Users\\User\\.lmstudio\\bin;C:\\Users\\User\\.dotnet\\tools;C:\\Users\\User\\AppData\\Local\\Programs\\Windsurf\\bin;C:\\Users\\User\\AppData\\Local\\reflex\\bun\\bin;C:\\Users\\User\\AppData\\Local\\Programs\\MiKTeX\\miktex\\bin\\x64\\;C:\\Users\\User\\AppData\\Roaming\\npm;C:\\Users\\User\\go\\bin;C:\\Users\\User\\AppData\\Local\\PowerToys\\" OLLAMA_LIBRARY_PATH=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13 time=2025-10-29T21:44:12.161-04:00 level=INFO source=runner.go:1337 msg="starting ollama engine" time=2025-10-29T21:44:12.162-04:00 level=INFO source=runner.go:1372 msg="Server listening on 127.0.0.1:60955" time=2025-10-29T21:44:12.166-04:00 level=DEBUG source=gguf.go:590 msg=general.architecture type=string time=2025-10-29T21:44:12.166-04:00 level=DEBUG source=gguf.go:590 msg=tokenizer.ggml.model type=string time=2025-10-29T21:44:12.167-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32 time=2025-10-29T21:44:12.168-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32 time=2025-10-29T21:44:12.168-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.file_type default=0 time=2025-10-29T21:44:12.168-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.name default="" time=2025-10-29T21:44:12.168-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.description default="" time=2025-10-29T21:44:12.169-04:00 level=INFO source=ggml.go:135 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3 time=2025-10-29T21:44:12.169-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama load_backend: loaded CPU backend from C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll time=2025-10-29T21:44:12.197-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13 ggml_cuda_init: failed to initialize CUDA: (null) load_backend: loaded CUDA backend from C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13\ggml-cuda.dll time=2025-10-29T21:44:12.283-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(clang) time=2025-10-29T21:44:12.284-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.block_count default=0 time=2025-10-29T21:44:12.284-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.pooling_type default=0 time=2025-10-29T21:44:12.284-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.expert_count default=0 time=2025-10-29T21:44:12.284-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}" time=2025-10-29T21:44:12.284-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}" time=2025-10-29T21:44:12.284-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}" time=2025-10-29T21:44:12.284-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}" time=2025-10-29T21:44:12.284-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true time=2025-10-29T21:44:12.284-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0 time=2025-10-29T21:44:12.284-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false time=2025-10-29T21:44:12.284-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0 time=2025-10-29T21:44:12.284-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}" time=2025-10-29T21:44:12.284-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.pre default="" time=2025-10-29T21:44:12.285-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.block_count default=0 time=2025-10-29T21:44:12.285-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.embedding_length default=0 time=2025-10-29T21:44:12.285-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.head_count default=0 time=2025-10-29T21:44:12.285-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.head_count_kv default=0 time=2025-10-29T21:44:12.285-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.key_length default=0 time=2025-10-29T21:44:12.285-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.rope.dimension_count default=0 time=2025-10-29T21:44:12.285-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0 time=2025-10-29T21:44:12.285-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.rope.freq_base default=100000 time=2025-10-29T21:44:12.285-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.rope.scaling.factor default=1 time=2025-10-29T21:44:12.285-04:00 level=DEBUG source=runner.go:1312 msg="dummy model load took" duration=119.2606ms time=2025-10-29T21:44:12.285-04:00 level=DEBUG source=runner.go:1317 msg="gathering device infos took" duration=0s time=2025-10-29T21:44:12.285-04:00 level=TRACE source=runner.go:498 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]" devices=[] time=2025-10-29T21:44:12.286-04:00 level=DEBUG source=runner.go:468 msg="bootstrap discovery took" duration=189.4849ms OLLAMA_LIBRARY_PATH="[C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]" extra_envs=map[] time=2025-10-29T21:44:12.286-04:00 level=TRACE source=runner.go:471 msg="starting runner for device discovery" libDirs="[C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm]" extraEnvs=map[] time=2025-10-29T21:44:12.288-04:00 level=INFO source=server.go:385 msg="starting runner" cmd="C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60962" time=2025-10-29T21:44:12.288-04:00 level=DEBUG source=server.go:386 msg=subprocess OLLAMA_MODELS=G:\OllamaFiles\models OLLAMA_DEBUG=2 OLLAMA_CONTEXT_LENGTH=16384 OLLAMA_AUTO_UPDATE=false OLLAMA_RAGTEMP=C:\OllamaRAGTemp PATH="C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm;C:\\Program Files\\PowerShell\\7;C:\\Program Files (x86)\\oh-my-posh\\bin\\;C:\\Users\\User\\Downloads\\vcmake\\vcpkg\\installed\\x64_windows;C:\\Program Files\\Common Files\\Oracle\\Java\\javapath;C:\\ActiveTcl\\bin;C:\\Program Files\\Microsoft MPI\\Bin\\;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314\\Scripts;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314\\tct\\tcl8.6;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314\\tcl;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313\\Scripts;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313\\tcl\\tcl8.6;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313\\tcl;C:\\Program Files\\OpenSSL\\bin;C:\\Users\\User\\AppData\\Roaming\\ActiveState\\bin;C:\\Windows\\system32;C:\\Windows;C:\\Windows\\System32\\Wbem;C:\\Windows\\System32\\WindowsPowerShell\\v1.0\\;C:\\Program Files\\Graphviz\\bin;C:\\Windows\\System32\\OpenSSH\\;C:\\Program Files\\Microsoft SQL Server\\130\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\170\\Tools\\Binn\\;C:\\Program Files\\dotnet\\;C:\\Program Files\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\150\\DTS\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\150\\DTS\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files\\Azure Data Studio\\bin;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\ProgramData\\chocolatey\\bin;C:\\Program Files\\Java\\jdk-21\\bin;C:\\Program Files\\NASM;C:\\Program Files\\Microsoft VS Code\\bin;C:\\Program Files\\gs\\gs10.03.0\\bin;C:\\Program Files (x86)\\Microsoft SQL Server\\160\\DTS\\Binn\\;C:\\Program Files\\PuTTY\\;C:\\Program Files\\RedHat\\Podman\\;C:\\TDM-GCC-64\\bin;D:\\home\\blt\\github\\vcpkg;C:\\Program Files\\CMake\\bin;C:\\Program Files\\nodejs\\;C:\\Program Files\\Go\\bin;C:\\Program Files\\Pandoc\\;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\Program Files\\PowerShell\\7\\;C:\\Program Files (x86)\\Windows Kits\\10\\Windows Performance Toolkit\\;C:\\Program Files\\Git\\cmd;C:\\Users\\User\\AppData\\Local\\Programs\\oh-my-posh\\bin\\;C:\\Users\\User\\.local\\bin;C:\\Users\\User\\AppData\\Local\\Programs\\Ollama;C:\\Users\\User\\Downloads\\vcmake\\vcpkg\\installed\\x64_windows;C:\\Users\\User\\.cargo\\bin;C:\\Program Files\\OpenSSL\\bin;C:\\Users\\User\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Program Files\\Azure Data Studio\\bin;C:\\Program Files\\PostgreSQL\\15\\bin;C:\\Users\\User\\AppData\\Local\\GitHubDesktop\\bin;C:\\Users\\User\\Downloads\\ffmpeg-master-latest-win64-gpl\\ffmpeg-master-latest-win64-gpl\\bin;C:\\Program Files\\Graphviz\\bin;c:\\Program Files\\zig;c:\\users\\user\\.local\\bin;C:\\Program Files (x86)\\Intel\\oneAPI;C:\\Users\\User\\go\\bin;C:\\Users\\User\\.lmstudio\\bin;C:\\Users\\User\\.dotnet\\tools;C:\\Users\\User\\AppData\\Local\\Programs\\Windsurf\\bin;C:\\Users\\User\\AppData\\Local\\reflex\\bun\\bin;C:\\Users\\User\\AppData\\Local\\Programs\\MiKTeX\\miktex\\bin\\x64\\;C:\\Users\\User\\AppData\\Roaming\\npm;C:\\Users\\User\\go\\bin;C:\\Users\\User\\AppData\\Local\\PowerToys\\" OLLAMA_LIBRARY_PATH=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\rocm time=2025-10-29T21:44:12.364-04:00 level=INFO source=runner.go:1337 msg="starting ollama engine" time=2025-10-29T21:44:12.366-04:00 level=INFO source=runner.go:1372 msg="Server listening on 127.0.0.1:60962" time=2025-10-29T21:44:12.375-04:00 level=DEBUG source=gguf.go:590 msg=general.architecture type=string time=2025-10-29T21:44:12.375-04:00 level=DEBUG source=gguf.go:590 msg=tokenizer.ggml.model type=string time=2025-10-29T21:44:12.375-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32 time=2025-10-29T21:44:12.377-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32 time=2025-10-29T21:44:12.377-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.file_type default=0 time=2025-10-29T21:44:12.377-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.name default="" time=2025-10-29T21:44:12.377-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.description default="" time=2025-10-29T21:44:12.377-04:00 level=INFO source=ggml.go:135 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3 time=2025-10-29T21:44:12.377-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama load_backend: loaded CPU backend from C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll time=2025-10-29T21:44:12.406-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\rocm ggml_cuda_init: failed to initialize ROCm: no ROCm-capable device is detected load_backend: loaded ROCm backend from C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\rocm\ggml-hip.dll time=2025-10-29T21:44:12.446-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(clang) time=2025-10-29T21:44:12.446-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.block_count default=0 time=2025-10-29T21:44:12.446-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.pooling_type default=0 time=2025-10-29T21:44:12.446-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.expert_count default=0 time=2025-10-29T21:44:12.446-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}" time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}" time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}" time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}" time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0 time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0 time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}" time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.pre default="" time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.block_count default=0 time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.embedding_length default=0 time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.head_count default=0 time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.head_count_kv default=0 time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.key_length default=0 time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.rope.dimension_count default=0 time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0 time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.rope.freq_base default=100000 time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.rope.scaling.factor default=1 time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=runner.go:1312 msg="dummy model load took" duration=72.7312ms time=2025-10-29T21:44:12.447-04:00 level=DEBUG source=runner.go:1317 msg="gathering device infos took" duration=0s time=2025-10-29T21:44:12.448-04:00 level=TRACE source=runner.go:498 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm]" devices=[] time=2025-10-29T21:44:12.448-04:00 level=DEBUG source=runner.go:468 msg="bootstrap discovery took" duration=162.4718ms OLLAMA_LIBRARY_PATH="[C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm]" extra_envs=map[] time=2025-10-29T21:44:12.448-04:00 level=DEBUG source=runner.go:120 msg="evluating which if any devices to filter out" initial_count=0 time=2025-10-29T21:44:12.448-04:00 level=TRACE source=runner.go:179 msg="supported GPU library combinations before filtering" supported=map[] time=2025-10-29T21:44:12.448-04:00 level=DEBUG source=runner.go:41 msg="GPU bootstrap discovery took" duration=661.722ms time=2025-10-29T21:44:12.449-04:00 level=INFO source=types.go:60 msg="inference compute" id=cpu library=cpu compute="" name=cpu description=cpu libdirs=ollama driver="" pci_id="" type="" total="11.9 GiB" available="6.0 GiB" time=2025-10-29T21:44:12.449-04:00 level=INFO source=routes.go:1618 msg="entering low vram mode" "total vram"="0 B" threshold="20.0 GiB" [GIN] 2025/10/29 - 21:44:12 | 200 | 541µs | 127.0.0.1 | HEAD "/" [GIN] 2025/10/29 - 21:44:12 | 200 | 57.0626ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/10/29 - 21:44:24 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2025/10/29 - 21:44:24 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2025/10/29 - 21:44:24 | 200 | 185.0917ms | 127.0.0.1 | GET "/api/tags" time=2025-10-29T21:44:25.105-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32 [GIN] 2025/10/29 - 21:44:25 | 200 | 254.2493ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/10/29 - 21:44:40 | 200 | 0s | 127.0.0.1 | GET "/api/version" time=2025-10-29T21:44:40.843-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32 [GIN] 2025/10/29 - 21:44:40 | 200 | 250.6383ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/10/29 - 21:44:40 | 200 | 106.9248ms | 127.0.0.1 | GET "/api/tags" time=2025-10-29T21:44:41.009-04:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32 [GIN] 2025/10/29 - 21:44:41 | 200 | 166.299ms | 127.0.0.1 | POST "/api/show" time=2025-10-29T21:44:41.196-04:00 level=DEBUG source=runner.go:267 msg="refreshing free memory" time=2025-10-29T21:44:41.196-04:00 level=DEBUG source=runner.go:41 msg="overall device VRAM discovery took" duration=0s [GIN] 2025/10/29 - 21:45:10 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2025/10/29 - 21:45:11 | 200 | 78.7139ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/10/29 - 21:45:41 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2025/10/29 - 21:45:41 | 200 | 52.8417ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/10/29 - 21:46:11 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2025/10/29 - 21:46:11 | 200 | 74.5929ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/10/29 - 21:46:41 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2025/10/29 - 21:46:41 | 200 | 199.5415ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/10/29 - 21:47:11 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2025/10/29 - 21:47:11 | 200 | 70.797ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/10/29 - 21:47:14 | 200 | 31.5551ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/10/29 - 21:47:23 | 200 | 33.352ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/10/29 - 21:47:23 | 200 | 35.7424ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/10/29 - 21:47:25 | 200 | 1.3314975s | 127.0.0.1 | POST "/api/chat" [GIN] 2025/10/29 - 21:47:27 | 200 | 814.5542ms | 127.0.0.1 | POST "/api/chat" [GIN] 2025/10/29 - 21:47:28 | 200 | 1.1260067s | 127.0.0.1 | POST "/api/chat" [GIN] 2025/10/29 - 21:47:30 | 200 | 1.6694057s | 127.0.0.1 | POST "/api/chat" [GIN] 2025/10/29 - 21:47:41 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2025/10/29 - 21:47:41 | 200 | 55.0317ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/10/29 - 21:48:11 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2025/10/29 - 21:48:11 | 200 | 52.7654ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/10/29 - 21:48:41 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2025/10/29 - 21:48:41 | 200 | 49.1216ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/10/29 - 21:49:11 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2025/10/29 - 21:49:11 | 200 | 60.5865ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/10/29 - 21:49:41 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2025/10/29 - 21:49:41 | 200 | 54.8271ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/10/29 - 21:50:11 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2025/10/29 - 21:50:11 | 200 | 58.8494ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/10/29 - 21:50:42 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2025/10/29 - 21:50:42 | 200 | 53.4373ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/10/29 - 21:51:12 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2025/10/29 - 21:51:12 | 200 | 54.2343ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/10/29 - 21:51:42 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2025/10/29 - 21:51:42 | 200 | 59.3495ms | 127.0.0.1 | GET "/api/tags" time=2025-10-29T21:44:10.544-04:00 level=INFO source=app_windows.go:270 msg="starting Ollama" app=C:\Users\User\AppData\Local\Programs\Ollama version=0.12.7 OS=Windows/10.0.19045 time=2025-10-29T21:44:10.546-04:00 level=INFO source=app.go:231 msg="initialized tools registry" tool_count=0 time=2025-10-29T21:44:10.587-04:00 level=INFO source=app.go:246 msg="starting ollama server" time=2025-10-29T21:44:10.931-04:00 level=INFO source=app.go:275 msg="starting ui server" port=60942 time=2025-10-29T21:44:10.953-04:00 level=INFO source=app.go:336 msg="deferring pending update for fast startup" time=2025-10-29T21:44:13.931-04:00 level=INFO source=updater.go:252 msg="beginning update checker" interval=1h0m0s time=2025-10-29T21:44:24.714-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=0s request_id=1761788664714383500 version=0.12.7 time=2025-10-29T21:44:24.719-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/me http.pattern="GET /api/v1/me" http.status=200 http.d=84.5648ms request_id=1761788664634994100 version=0.12.7 time=2025-10-29T21:44:24.733-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/health http.pattern="GET /api/v1/health" http.status=200 http.d=11.0824ms request_id=1761788664722425600 version=0.12.7 time=2025-10-29T21:44:24.749-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/chats http.pattern="GET /api/v1/chats" http.status=200 http.d=24.2975ms request_id=1761788664725422700 version=0.12.7 time=2025-10-29T21:44:24.762-04:00 level=INFO source=server.go:343 msg=Matched "inference compute"="{Library:cpu Variant: Compute: Driver: Name:cpu VRAM:11.9 GiB}" time=2025-10-29T21:44:24.762-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/inference-compute http.pattern="GET /api/v1/inference-compute" http.status=200 http.d=43.6747ms request_id=1761788664718542400 version=0.12.7 time=2025-10-29T21:44:24.915-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=199.1878ms request_id=1761788664716368200 version=0.12.7 time=2025-10-29T21:44:24.984-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/chats http.pattern="GET /api/v1/chats" http.status=200 http.d=25.1705ms request_id=1761788664959127700 version=0.12.7 time=2025-10-29T21:44:25.117-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/model/qwen3:4b/capabilities http.pattern="GET /api/v1/model/{model}/capabilities" http.status=200 http.d=264.7715ms request_id=1761788664853051300 version=0.12.7 time=2025-10-29T21:44:25.399-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=POST http.path=/api/v1/model/upstream http.pattern="POST /api/v1/model/upstream" http.status=200 http.d=162.7553ms request_id=1761788665236699300 version=0.12.7 time=2025-10-29T21:44:40.658-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/chats http.pattern="GET /api/v1/chats" http.status=200 http.d=23.821ms request_id=1761788680635163500 version=0.12.7 time=2025-10-29T21:44:40.767-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=1.3556ms request_id=1761788680766282800 version=0.12.7 time=2025-10-29T21:44:40.878-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=111.7008ms request_id=1761788680767101300 version=0.12.7 time=2025-10-29T21:45:11.007-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=86.2728ms request_id=1761788710921244800 version=0.12.7 time=2025-10-29T21:45:41.072-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=58.9496ms request_id=1761788741013530600 version=0.12.7 time=2025-10-29T21:46:11.160-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=81.4457ms request_id=1761788771078929500 version=0.12.7 time=2025-10-29T21:46:41.391-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=212.4071ms request_id=1761788801178638100 version=0.12.7 time=2025-10-29T21:47:08.047-04:00 level=ERROR source=ui.go:1179 msg="chat stream error" error="Post \"http://127.0.0.1:11434/api/chat\": context canceled" time=2025-10-29T21:47:08.047-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=POST http.path=/api/v1/chat/new http.pattern="POST /api/v1/chat/{id}" http.status=200 http.d=2m27.4542528s request_id=1761788680592933600 version=0.12.7 time=2025-10-29T21:47:11.535-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=79.1006ms request_id=1761788831456019700 version=0.12.7 time=2025-10-29T21:47:14.028-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=POST http.path=/api/v1/settings http.pattern="POST /api/v1/settings" http.status=200 http.d=594µs request_id=1761788834028069900 version=0.12.7 time=2025-10-29T21:47:14.035-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/settings http.pattern="GET /api/v1/settings" http.status=200 http.d=0s request_id=1761788834035388500 version=0.12.7 time=2025-10-29T21:47:14.084-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/model/gpt-oss:20b-cloud/capabilities http.pattern="GET /api/v1/model/{model}/capabilities" http.status=200 http.d=31.9895ms request_id=1761788834052226600 version=0.12.7 time=2025-10-29T21:47:14.396-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=POST http.path=/api/v1/model/upstream http.pattern="POST /api/v1/model/upstream" http.status=200 http.d=351.1287ms request_id=1761788834045034700 version=0.12.7 time=2025-10-29T21:47:30.128-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=POST http.path=/api/v1/chat/019a32c9-d991-770c-882b-2ab0187daa95 http.pattern="POST /api/v1/chat/{id}" http.status=200 http.d=6.3121519s request_id=1761788843815980500 version=0.12.7 time=2025-10-29T21:47:30.138-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/chat/019a32c9-d991-770c-882b-2ab0187daa95 http.pattern="GET /api/v1/chat/{id}" http.status=200 http.d=9.1821ms request_id=1761788850129584200 version=0.12.7 time=2025-10-29T21:47:41.608-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=61.4188ms request_id=1761788861546597500 version=0.12.7 time=2025-10-29T21:48:11.680-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=58.3517ms request_id=1761788891622309800 version=0.12.7 time=2025-10-29T21:48:41.752-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=51.5636ms request_id=1761788921700600300 version=0.12.7 time=2025-10-29T21:49:11.828-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=66.4161ms request_id=1761788951762197100 version=0.12.7 time=2025-10-29T21:49:41.898-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=56.9438ms request_id=1761788981841884900 version=0.12.7 time=2025-10-29T21:50:11.983-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=65.2983ms request_id=1761789011918117000 version=0.12.7 time=2025-10-29T21:50:42.065-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=57.7472ms request_id=1761789042007958300 version=0.12.7 time=2025-10-29T21:51:12.137-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=56.72ms request_id=1761789072080460500 version=0.12.7 time=2025-10-29T21:51:42.216-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=63.3792ms request_id=1761789102152736300 version=0.12.7 time=2025-10-29T21:52:12.303-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=71.2135ms request_id=1761789132232153000 version=0.12.7 time=2025-10-29T21:52:42.392-04:00 level=INFO source=ui.go:168 msg=site.serveHTTP http.method=GET http.path=/api/v1/models http.pattern="GET /api/v1/models" http.status=200 http.d=65.8005ms request_id=1761789162327049800 version=0.12.7
GiteaMirror commented 2026-04-22 17:28:37 -05:00
Author
Owner
Copy Link

@Panican-Whyasker commented on GitHub (Oct 31, 2025):

Please give 0.12.7 a try and let us know if the issues are resolved. If not, please share an updated log with OLLAMA_DEBUG=2 set so we can take a look.

Waiting forever to load a 0.6B model in Ollama 0.12.7 on a Win11Pro laptop w. 5th-Gen Core i7 CPU, 8 GB of RAM, with nVidia GeForce M840 GPU with 2 GB of own VRAM:

Image

OLLAMA_DEBUG=2 was added to Environment Variables:

Image

At present time 08:23AM, here is the

app.log:

time=2025-10-31T08:08:00.575+01:00 level=INFO source=app_windows.go:270 msg="starting Ollama" app=C:\Users\Joro\AppData\Local\Programs\Ollama version=0.12.7 OS=Windows/10.0.26100
time=2025-10-31T08:08:00.583+01:00 level=INFO source=app.go:231 msg="initialized tools registry" tool_count=0
time=2025-10-31T08:08:00.616+01:00 level=INFO source=app.go:246 msg="starting ollama server"
time=2025-10-31T08:08:00.965+01:00 level=INFO source=app.go:275 msg="starting ui server" port=53147
time=2025-10-31T08:08:03.966+01:00 level=INFO source=updater.go:252 msg="beginning update checker" interval=1h0m0s

...as well as the

server.log:

time=2025-10-31T08:08:02.049+01:00 level=INFO source=routes.go:1524 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:DEBUG-4 OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\Users\Joro\.ollama\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]"
time=2025-10-31T08:08:02.110+01:00 level=INFO source=images.go:522 msg="total blobs: 12"
time=2025-10-31T08:08:02.113+01:00 level=INFO source=images.go:529 msg="total unused blobs removed: 0"
time=2025-10-31T08:08:02.119+01:00 level=INFO source=routes.go:1577 msg="Listening on 127.0.0.1:11434 (version 0.12.7)"
time=2025-10-31T08:08:02.120+01:00 level=DEBUG source=sched.go:120 msg="starting llm scheduler"
time=2025-10-31T08:08:02.125+01:00 level=INFO source=runner.go:76 msg="discovering available GPUs..."
time=2025-10-31T08:08:02.126+01:00 level=TRACE source=runner.go:471 msg="starting runner for device discovery" libDirs="[C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12]" extraEnvs=map[]
time=2025-10-31T08:08:02.148+01:00 level=INFO source=server.go:385 msg="starting runner" cmd="C:\Users\Joro\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 53150"
time=2025-10-31T08:08:02.149+01:00 level=DEBUG source=server.go:386 msg=subprocess OLLAMA_CONTEXT_LENGTH=4096 PATH="C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12;C:\WINDOWS\system32;C:\WINDOWS;C:\WINDOWS\System32\Wbem;C:\WINDOWS\System32\WindowsPowerShell\v1.0\;C:\WINDOWS\System32\OpenSSH\;C:\Program Files (x86)\NVIDIA Corporation\PhysX\Common;C:\Program Files\PowerShell\7\;C:\Users\Joro\AppData\Local\Microsoft\WindowsApps;;C:\Users\Joro\AppData\Local\Programs\Ollama" OLLAMA_DEBUG=2 OLLAMA_MODELS=C:\Users\Joro.ollama\models OLLAMA_LIBRARY_PATH=C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12
time=2025-10-31T08:08:02.226+01:00 level=INFO source=runner.go:1337 msg="starting ollama engine"
time=2025-10-31T08:08:02.231+01:00 level=INFO source=runner.go:1372 msg="Server listening on 127.0.0.1:53150"
time=2025-10-31T08:08:02.244+01:00 level=DEBUG source=gguf.go:590 msg=general.architecture type=string
time=2025-10-31T08:08:02.245+01:00 level=DEBUG source=gguf.go:590 msg=tokenizer.ggml.model type=string
time=2025-10-31T08:08:02.246+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32
time=2025-10-31T08:08:02.259+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32
time=2025-10-31T08:08:02.259+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.file_type default=0
time=2025-10-31T08:08:02.259+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.name default=""
time=2025-10-31T08:08:02.259+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.description default=""
time=2025-10-31T08:08:02.260+01:00 level=INFO source=ggml.go:135 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
time=2025-10-31T08:08:02.260+01:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama
load_backend: loaded CPU backend from C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll
time=2025-10-31T08:08:02.955+01:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12
time=2025-10-31T08:08:32.127+01:00 level=INFO source=runner.go:495 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12]" extra_envs=map[] error="failed to finish discovery before timeout"
time=2025-10-31T08:08:32.127+01:00 level=TRACE source=runner.go:498 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12]" devices=[]
time=2025-10-31T08:08:32.127+01:00 level=DEBUG source=runner.go:468 msg="bootstrap discovery took" duration=30.0015049s OLLAMA_LIBRARY_PATH="[C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12]" extra_envs=map[]
time=2025-10-31T08:08:32.127+01:00 level=TRACE source=runner.go:471 msg="starting runner for device discovery" libDirs="[C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13]" extraEnvs=map[]
time=2025-10-31T08:08:32.133+01:00 level=INFO source=server.go:385 msg="starting runner" cmd="C:\Users\Joro\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 62942"
time=2025-10-31T08:08:32.133+01:00 level=DEBUG source=server.go:386 msg=subprocess OLLAMA_CONTEXT_LENGTH=4096 PATH="C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13;C:\WINDOWS\system32;C:\WINDOWS;C:\WINDOWS\System32\Wbem;C:\WINDOWS\System32\WindowsPowerShell\v1.0\;C:\WINDOWS\System32\OpenSSH\;C:\Program Files (x86)\NVIDIA Corporation\PhysX\Common;C:\Program Files\PowerShell\7\;C:\Users\Joro\AppData\Local\Microsoft\WindowsApps;;C:\Users\Joro\AppData\Local\Programs\Ollama" OLLAMA_DEBUG=2 OLLAMA_MODELS=C:\Users\Joro.ollama\models OLLAMA_LIBRARY_PATH=C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13
time=2025-10-31T08:08:32.194+01:00 level=INFO source=runner.go:1337 msg="starting ollama engine"
time=2025-10-31T08:08:32.196+01:00 level=INFO source=runner.go:1372 msg="Server listening on 127.0.0.1:62942"
time=2025-10-31T08:08:32.201+01:00 level=DEBUG source=gguf.go:590 msg=general.architecture type=string
time=2025-10-31T08:08:32.201+01:00 level=DEBUG source=gguf.go:590 msg=tokenizer.ggml.model type=string
time=2025-10-31T08:08:32.202+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32
time=2025-10-31T08:08:32.203+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32
time=2025-10-31T08:08:32.203+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.file_type default=0
time=2025-10-31T08:08:32.203+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.name default=""
time=2025-10-31T08:08:32.203+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.description default=""
time=2025-10-31T08:08:32.203+01:00 level=INFO source=ggml.go:135 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
time=2025-10-31T08:08:32.203+01:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama
load_backend: loaded CPU backend from C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll
time=2025-10-31T08:08:32.232+01:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13
time=2025-10-31T08:09:04.206+01:00 level=INFO source=runner.go:495 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13]" extra_envs=map[] error="failed to finish discovery before timeout"
time=2025-10-31T08:09:04.206+01:00 level=TRACE source=runner.go:498 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13]" devices=[]
time=2025-10-31T08:09:04.206+01:00 level=DEBUG source=runner.go:468 msg="bootstrap discovery took" duration=32.0789732s OLLAMA_LIBRARY_PATH="[C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13]" extra_envs=map[]
time=2025-10-31T08:09:04.206+01:00 level=TRACE source=runner.go:471 msg="starting runner for device discovery" libDirs="[C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\rocm]" extraEnvs=map[]
time=2025-10-31T08:09:04.243+01:00 level=INFO source=server.go:385 msg="starting runner" cmd="C:\Users\Joro\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 62949"
time=2025-10-31T08:09:04.243+01:00 level=DEBUG source=server.go:386 msg=subprocess OLLAMA_CONTEXT_LENGTH=4096 PATH="C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\rocm;C:\WINDOWS\system32;C:\WINDOWS;C:\WINDOWS\System32\Wbem;C:\WINDOWS\System32\WindowsPowerShell\v1.0\;C:\WINDOWS\System32\OpenSSH\;C:\Program Files (x86)\NVIDIA Corporation\PhysX\Common;C:\Program Files\PowerShell\7\;C:\Users\Joro\AppData\Local\Microsoft\WindowsApps;;C:\Users\Joro\AppData\Local\Programs\Ollama" OLLAMA_DEBUG=2 OLLAMA_MODELS=C:\Users\Joro.ollama\models OLLAMA_LIBRARY_PATH=C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\rocm
time=2025-10-31T08:09:21.729+01:00 level=INFO source=runner.go:1337 msg="starting ollama engine"
time=2025-10-31T08:09:21.732+01:00 level=INFO source=runner.go:1372 msg="Server listening on 127.0.0.1:62949"
time=2025-10-31T08:09:21.817+01:00 level=DEBUG source=gguf.go:590 msg=general.architecture type=string
time=2025-10-31T08:09:21.817+01:00 level=DEBUG source=gguf.go:590 msg=tokenizer.ggml.model type=string
time=2025-10-31T08:09:21.817+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32
time=2025-10-31T08:09:21.819+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32
time=2025-10-31T08:09:21.819+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.file_type default=0
time=2025-10-31T08:09:21.819+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.name default=""
time=2025-10-31T08:09:21.819+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.description default=""
time=2025-10-31T08:09:21.819+01:00 level=INFO source=ggml.go:135 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
time=2025-10-31T08:09:21.819+01:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama
load_backend: loaded CPU backend from C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll
time=2025-10-31T08:09:21.852+01:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\rocm
time=2025-10-31T08:10:04.207+01:00 level=INFO source=runner.go:495 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\rocm]" extra_envs=map[] error="failed to finish discovery before timeout"
time=2025-10-31T08:10:04.207+01:00 level=TRACE source=runner.go:498 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\rocm]" devices=[]
time=2025-10-31T08:10:04.207+01:00 level=DEBUG source=runner.go:468 msg="bootstrap discovery took" duration=1m0.0009716s OLLAMA_LIBRARY_PATH="[C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\rocm]" extra_envs=map[]
time=2025-10-31T08:10:04.207+01:00 level=DEBUG source=runner.go:120 msg="evluating which if any devices to filter out" initial_count=0
time=2025-10-31T08:10:04.208+01:00 level=TRACE source=runner.go:179 msg="supported GPU library combinations before filtering" supported=map[]
time=2025-10-31T08:10:04.208+01:00 level=DEBUG source=runner.go:41 msg="GPU bootstrap discovery took" duration=2m2.0872522s
time=2025-10-31T08:10:04.209+01:00 level=INFO source=types.go:60 msg="inference compute" id=cpu library=cpu compute="" name=cpu description=cpu libdirs=ollama driver="" pci_id="" type="" total="7.9 GiB" available="802.4 MiB"
time=2025-10-31T08:10:04.209+01:00 level=INFO source=routes.go:1618 msg="entering low vram mode" "total vram"="0 B" threshold="20.0 GiB"
[GIN] 2025/10/31 - 08:12:58 | 200 | 8.1601ms | 127.0.0.1 | GET "/api/version"
[GIN] 2025/10/31 - 08:13:03 | 200 | 0s | 127.0.0.1 | HEAD "/"
[GIN] 2025/10/31 - 08:13:03 | 200 | 38.5777ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2025/10/31 - 08:13:24 | 200 | 0s | 127.0.0.1 | HEAD "/"
time=2025-10-31T08:13:24.904+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32
[GIN] 2025/10/31 - 08:13:24 | 200 | 173.1176ms | 127.0.0.1 | POST "/api/show"
time=2025-10-31T08:13:25.046+01:00 level=DEBUG source=runner.go:267 msg="refreshing free memory"
time=2025-10-31T08:13:25.046+01:00 level=DEBUG source=runner.go:41 msg="overall device VRAM discovery took" duration=0s

<!-- gh-comment-id:3471619561 --> @Panican-Whyasker commented on GitHub (Oct 31, 2025): > Please give 0.12.7 a try and let us know if the issues are resolved. If not, please share an updated log with OLLAMA_DEBUG=2 set so we can take a look. Waiting forever to load a 0.6B model in Ollama 0.12.7 on a Win11Pro laptop w. 5th-Gen Core i7 CPU, 8 GB of RAM, with nVidia GeForce M840 GPU with 2 GB of own VRAM: ![Image](https://github.com/user-attachments/assets/36bb8719-adbf-405e-bb89-92d7d3c67f21) OLLAMA_DEBUG=2 was added to Environment Variables: ![Image](https://github.com/user-attachments/assets/37b4574c-31a6-4926-8f49-886e9ce587a9) At present time 08:23AM, here is the app.log: time=2025-10-31T08:08:00.575+01:00 level=INFO source=app_windows.go:270 msg="starting Ollama" app=C:\Users\Joro\AppData\Local\Programs\Ollama version=0.12.7 OS=Windows/10.0.26100 time=2025-10-31T08:08:00.583+01:00 level=INFO source=app.go:231 msg="initialized tools registry" tool_count=0 time=2025-10-31T08:08:00.616+01:00 level=INFO source=app.go:246 msg="starting ollama server" time=2025-10-31T08:08:00.965+01:00 level=INFO source=app.go:275 msg="starting ui server" port=53147 time=2025-10-31T08:08:03.966+01:00 level=INFO source=updater.go:252 msg="beginning update checker" interval=1h0m0s ...as well as the server.log: time=2025-10-31T08:08:02.049+01:00 level=INFO source=routes.go:1524 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:DEBUG-4 OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\\Users\\Joro\\.ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]" time=2025-10-31T08:08:02.110+01:00 level=INFO source=images.go:522 msg="total blobs: 12" time=2025-10-31T08:08:02.113+01:00 level=INFO source=images.go:529 msg="total unused blobs removed: 0" time=2025-10-31T08:08:02.119+01:00 level=INFO source=routes.go:1577 msg="Listening on 127.0.0.1:11434 (version 0.12.7)" time=2025-10-31T08:08:02.120+01:00 level=DEBUG source=sched.go:120 msg="starting llm scheduler" time=2025-10-31T08:08:02.125+01:00 level=INFO source=runner.go:76 msg="discovering available GPUs..." time=2025-10-31T08:08:02.126+01:00 level=TRACE source=runner.go:471 msg="starting runner for device discovery" libDirs="[C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" extraEnvs=map[] time=2025-10-31T08:08:02.148+01:00 level=INFO source=server.go:385 msg="starting runner" cmd="C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 53150" time=2025-10-31T08:08:02.149+01:00 level=DEBUG source=server.go:386 msg=subprocess OLLAMA_CONTEXT_LENGTH=4096 PATH="C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common;C:\\Program Files\\PowerShell\\7\\;C:\\Users\\Joro\\AppData\\Local\\Microsoft\\WindowsApps;;C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama" OLLAMA_DEBUG=2 OLLAMA_MODELS=C:\Users\Joro\.ollama\models OLLAMA_LIBRARY_PATH=C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12 time=2025-10-31T08:08:02.226+01:00 level=INFO source=runner.go:1337 msg="starting ollama engine" time=2025-10-31T08:08:02.231+01:00 level=INFO source=runner.go:1372 msg="Server listening on 127.0.0.1:53150" time=2025-10-31T08:08:02.244+01:00 level=DEBUG source=gguf.go:590 msg=general.architecture type=string time=2025-10-31T08:08:02.245+01:00 level=DEBUG source=gguf.go:590 msg=tokenizer.ggml.model type=string time=2025-10-31T08:08:02.246+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32 time=2025-10-31T08:08:02.259+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32 time=2025-10-31T08:08:02.259+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.file_type default=0 time=2025-10-31T08:08:02.259+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.name default="" time=2025-10-31T08:08:02.259+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.description default="" time=2025-10-31T08:08:02.260+01:00 level=INFO source=ggml.go:135 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3 time=2025-10-31T08:08:02.260+01:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama load_backend: loaded CPU backend from C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll time=2025-10-31T08:08:02.955+01:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12 time=2025-10-31T08:08:32.127+01:00 level=INFO source=runner.go:495 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" extra_envs=map[] error="failed to finish discovery before timeout" time=2025-10-31T08:08:32.127+01:00 level=TRACE source=runner.go:498 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" devices=[] time=2025-10-31T08:08:32.127+01:00 level=DEBUG source=runner.go:468 msg="bootstrap discovery took" duration=30.0015049s OLLAMA_LIBRARY_PATH="[C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" extra_envs=map[] time=2025-10-31T08:08:32.127+01:00 level=TRACE source=runner.go:471 msg="starting runner for device discovery" libDirs="[C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]" extraEnvs=map[] time=2025-10-31T08:08:32.133+01:00 level=INFO source=server.go:385 msg="starting runner" cmd="C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62942" time=2025-10-31T08:08:32.133+01:00 level=DEBUG source=server.go:386 msg=subprocess OLLAMA_CONTEXT_LENGTH=4096 PATH="C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common;C:\\Program Files\\PowerShell\\7\\;C:\\Users\\Joro\\AppData\\Local\\Microsoft\\WindowsApps;;C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama" OLLAMA_DEBUG=2 OLLAMA_MODELS=C:\Users\Joro\.ollama\models OLLAMA_LIBRARY_PATH=C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13 time=2025-10-31T08:08:32.194+01:00 level=INFO source=runner.go:1337 msg="starting ollama engine" time=2025-10-31T08:08:32.196+01:00 level=INFO source=runner.go:1372 msg="Server listening on 127.0.0.1:62942" time=2025-10-31T08:08:32.201+01:00 level=DEBUG source=gguf.go:590 msg=general.architecture type=string time=2025-10-31T08:08:32.201+01:00 level=DEBUG source=gguf.go:590 msg=tokenizer.ggml.model type=string time=2025-10-31T08:08:32.202+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32 time=2025-10-31T08:08:32.203+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32 time=2025-10-31T08:08:32.203+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.file_type default=0 time=2025-10-31T08:08:32.203+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.name default="" time=2025-10-31T08:08:32.203+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.description default="" time=2025-10-31T08:08:32.203+01:00 level=INFO source=ggml.go:135 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3 time=2025-10-31T08:08:32.203+01:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama load_backend: loaded CPU backend from C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll time=2025-10-31T08:08:32.232+01:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13 time=2025-10-31T08:09:04.206+01:00 level=INFO source=runner.go:495 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]" extra_envs=map[] error="failed to finish discovery before timeout" time=2025-10-31T08:09:04.206+01:00 level=TRACE source=runner.go:498 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]" devices=[] time=2025-10-31T08:09:04.206+01:00 level=DEBUG source=runner.go:468 msg="bootstrap discovery took" duration=32.0789732s OLLAMA_LIBRARY_PATH="[C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]" extra_envs=map[] time=2025-10-31T08:09:04.206+01:00 level=TRACE source=runner.go:471 msg="starting runner for device discovery" libDirs="[C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm]" extraEnvs=map[] time=2025-10-31T08:09:04.243+01:00 level=INFO source=server.go:385 msg="starting runner" cmd="C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62949" time=2025-10-31T08:09:04.243+01:00 level=DEBUG source=server.go:386 msg=subprocess OLLAMA_CONTEXT_LENGTH=4096 PATH="C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common;C:\\Program Files\\PowerShell\\7\\;C:\\Users\\Joro\\AppData\\Local\\Microsoft\\WindowsApps;;C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama" OLLAMA_DEBUG=2 OLLAMA_MODELS=C:\Users\Joro\.ollama\models OLLAMA_LIBRARY_PATH=C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\rocm time=2025-10-31T08:09:21.729+01:00 level=INFO source=runner.go:1337 msg="starting ollama engine" time=2025-10-31T08:09:21.732+01:00 level=INFO source=runner.go:1372 msg="Server listening on 127.0.0.1:62949" time=2025-10-31T08:09:21.817+01:00 level=DEBUG source=gguf.go:590 msg=general.architecture type=string time=2025-10-31T08:09:21.817+01:00 level=DEBUG source=gguf.go:590 msg=tokenizer.ggml.model type=string time=2025-10-31T08:09:21.817+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32 time=2025-10-31T08:09:21.819+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32 time=2025-10-31T08:09:21.819+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.file_type default=0 time=2025-10-31T08:09:21.819+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.name default="" time=2025-10-31T08:09:21.819+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.description default="" time=2025-10-31T08:09:21.819+01:00 level=INFO source=ggml.go:135 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3 time=2025-10-31T08:09:21.819+01:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama load_backend: loaded CPU backend from C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll time=2025-10-31T08:09:21.852+01:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\Joro\AppData\Local\Programs\Ollama\lib\ollama\rocm time=2025-10-31T08:10:04.207+01:00 level=INFO source=runner.go:495 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm]" extra_envs=map[] error="failed to finish discovery before timeout" time=2025-10-31T08:10:04.207+01:00 level=TRACE source=runner.go:498 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm]" devices=[] time=2025-10-31T08:10:04.207+01:00 level=DEBUG source=runner.go:468 msg="bootstrap discovery took" duration=1m0.0009716s OLLAMA_LIBRARY_PATH="[C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\Joro\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm]" extra_envs=map[] time=2025-10-31T08:10:04.207+01:00 level=DEBUG source=runner.go:120 msg="evluating which if any devices to filter out" initial_count=0 time=2025-10-31T08:10:04.208+01:00 level=TRACE source=runner.go:179 msg="supported GPU library combinations before filtering" supported=map[] time=2025-10-31T08:10:04.208+01:00 level=DEBUG source=runner.go:41 msg="GPU bootstrap discovery took" duration=2m2.0872522s time=2025-10-31T08:10:04.209+01:00 level=INFO source=types.go:60 msg="inference compute" id=cpu library=cpu compute="" name=cpu description=cpu libdirs=ollama driver="" pci_id="" type="" total="7.9 GiB" available="802.4 MiB" time=2025-10-31T08:10:04.209+01:00 level=INFO source=routes.go:1618 msg="entering low vram mode" "total vram"="0 B" threshold="20.0 GiB" [GIN] 2025/10/31 - 08:12:58 | 200 | 8.1601ms | 127.0.0.1 | GET "/api/version" [GIN] 2025/10/31 - 08:13:03 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2025/10/31 - 08:13:03 | 200 | 38.5777ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/10/31 - 08:13:24 | 200 | 0s | 127.0.0.1 | HEAD "/" time=2025-10-31T08:13:24.904+01:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32 [GIN] 2025/10/31 - 08:13:24 | 200 | 173.1176ms | 127.0.0.1 | POST "/api/show" time=2025-10-31T08:13:25.046+01:00 level=DEBUG source=runner.go:267 msg="refreshing free memory" time=2025-10-31T08:13:25.046+01:00 level=DEBUG source=runner.go:41 msg="overall device VRAM discovery took" duration=0s
GiteaMirror commented 2026-04-22 17:28:40 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Oct 31, 2025):

I made a small fix to some logging logic for Windows on 0.12.8 which likely wont fix this, but may help us get more details on the failure. Anyone still seeing the hang, please install 0.12.8 and set $env:OLLAMA_DEBUG="2" and share the server log from startup through a request that hangs so we can try to narrow down what's going wrong.

<!-- gh-comment-id:3473959843 --> @dhiltgen commented on GitHub (Oct 31, 2025): I made a small fix to some logging logic for Windows on 0.12.8 which likely wont fix this, but may help us get more details on the failure. Anyone still seeing the hang, please install 0.12.8 and set `$env:OLLAMA_DEBUG="2"` and share the server log from startup through a request that hangs so we can try to narrow down what's going wrong.
GiteaMirror commented 2026-04-22 17:28:42 -05:00
Author
Owner
Copy Link

@katmandoo212 commented on GitHub (Nov 1, 2025):

I ran 0.12.8 with OLLAMA_DEBUG=2 as suggested. Trying to run a local model hangs, but Cloud models work. I have attached my server.log and app.log.

app.log
server.log

<!-- gh-comment-id:3475284026 --> @katmandoo212 commented on GitHub (Nov 1, 2025): I ran 0.12.8 with OLLAMA_DEBUG=2 as suggested. Trying to run a local model hangs, but Cloud models work. I have attached my server.log and app.log. [app.log](https://github.com/user-attachments/files/23279576/app.log) [server.log](https://github.com/user-attachments/files/23279575/server.log)
GiteaMirror commented 2026-04-22 17:28:42 -05:00
Author
Owner
Copy Link

@katmandoo212 commented on GitHub (Nov 1, 2025):

Just to let everyone know, I tried 0.12.9 on Windows 10, no GPU and it still hangs (spinner spins) when loading local models, but cloud models do work.

<!-- gh-comment-id:3476663277 --> @katmandoo212 commented on GitHub (Nov 1, 2025): Just to let everyone know, I tried 0.12.9 on Windows 10, no GPU and it still hangs (spinner spins) when loading local models, but cloud models do work.
GiteaMirror commented 2026-04-22 17:28:43 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Nov 4, 2025):

It sounds like there's a deadlock someplace, but I'm not sure where the system is getting hung up. Lets try to isolate things a little more. @katmandoo212 can you quit the GUI app by exiting the tray application, then lets run the server and CLI in a terminal.

$env:OLLAMA_DEBUG="2"
ollama serve 2>&1 | % ToString | tee-object serve.log

then in another terminal

ollama run qwen3:1.7b hello

Also, when it gets into this stuck state, do you see the ollama serve chewing up a CPU core in Task Manager, or is the system completely idle?

Comparing logs with other systems, it seems like it may be gathering information about the CPUs in the system. Is there anything unusual about your CPU setup?

<!-- gh-comment-id:3487738991 --> @dhiltgen commented on GitHub (Nov 4, 2025): It sounds like there's a deadlock someplace, but I'm not sure where the system is getting hung up. Lets try to isolate things a little more. @katmandoo212 can you quit the GUI app by exiting the tray application, then lets run the server and CLI in a terminal. ```powershell $env:OLLAMA_DEBUG="2" ollama serve 2>&1 | % ToString | tee-object serve.log ``` then in another terminal ```powershell ollama run qwen3:1.7b hello ``` Also, when it gets into this stuck state, do you see the `ollama serve` chewing up a CPU core in Task Manager, or is the system completely idle? Comparing logs with other systems, it seems like it may be gathering information about the CPUs in the system. Is there anything unusual about your CPU setup?
GiteaMirror commented 2026-04-22 17:28:45 -05:00
Author
Owner
Copy Link

@katmandoo212 commented on GitHub (Nov 5, 2025):

Here is my server log from the latest run using your instructions.

$env:OLLAMA_DEBUG="2"
ollama serve 2>&1 | % ToString | tee-object serve.log

ollama run qwen3:1.7b hello

❯ ollama serve 2>&1 | % ToString | tee-object serve.log
time=2025-11-04T20:36:02.700-05:00 level=INFO source=routes.go:1524 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:DEBUG-4 OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:G:\\OllamaFiles\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]"
time=2025-11-04T20:36:05.637-05:00 level=INFO source=images.go:522 msg="total blobs: 374"
time=2025-11-04T20:36:05.687-05:00 level=INFO source=images.go:529 msg="total unused blobs removed: 0"
time=2025-11-04T20:36:05.719-05:00 level=INFO source=routes.go:1577 msg="Listening on 127.0.0.1:11434 (version 0.12.9)"
time=2025-11-04T20:36:05.719-05:00 level=DEBUG source=sched.go:120 msg="starting llm scheduler"
time=2025-11-04T20:36:05.726-05:00 level=INFO source=runner.go:76 msg="discovering available GPUs..."
time=2025-11-04T20:36:05.726-05:00 level=TRACE source=runner.go:474 msg="starting runner for device discovery" libDirs="[C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" extraEnvs=map[]
time=2025-11-04T20:36:05.775-05:00 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 65308"
time=2025-11-04T20:36:05.775-05:00 level=DEBUG source=server.go:401 msg=subprocess OLLAMA_AUTO_UPDATE=false OLLAMA_DEBUG=2 OLLAMA_MODELS=G:\OllamaFiles\models OLLAMA_RAGTEMP=C:\OllamaRAGTemp PATH="C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12;C:\\Program Files\\PowerShell\\7;C:\\Program Files (x86)\\oh-my-posh\\bin\\;C:\\Users\\User\\Downloads\\vcmake\\vcpkg\\installed\\x64_windows;C:\\Program Files\\Common Files\\Oracle\\Java\\javapath;C:\\ActiveTcl\\bin;C:\\Program Files\\Microsoft MPI\\Bin\\;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314\\Scripts;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314\\tct\\tcl8.6;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314\\tcl;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313\\Scripts;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313\\tcl\\tcl8.6;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313\\tcl;C:\\Program Files\\OpenSSL\\bin;C:\\Users\\User\\AppData\\Roaming\\ActiveState\\bin;C:\\Windows\\system32;C:\\Windows;C:\\Windows\\System32\\Wbem;C:\\Windows\\System32\\WindowsPowerShell\\v1.0\\;C:\\Program Files\\Graphviz\\bin;C:\\Windows\\System32\\OpenSSH\\;C:\\Program Files\\Microsoft SQL Server\\130\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\170\\Tools\\Binn\\;C:\\Program Files\\dotnet\\;C:\\Program Files\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\150\\DTS\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\150\\DTS\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files\\Azure Data Studio\\bin;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\ProgramData\\chocolatey\\bin;C:\\Program Files\\Java\\jdk-21\\bin;C:\\Program Files\\NASM;C:\\Program Files\\Microsoft VS Code\\bin;C:\\Program Files\\gs\\gs10.03.0\\bin;C:\\Program Files (x86)\\Microsoft SQL Server\\160\\DTS\\Binn\\;C:\\Program Files\\PuTTY\\;C:\\Program Files\\RedHat\\Podman\\;C:\\TDM-GCC-64\\bin;D:\\home\\blt\\github\\vcpkg;C:\\Program Files\\CMake\\bin;C:\\Program Files\\nodejs\\;C:\\Program Files\\Go\\bin;C:\\Program Files\\Pandoc\\;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\Program Files\\PowerShell\\7\\;C:\\Program Files (x86)\\Windows Kits\\10\\Windows Performance Toolkit\\;C:\\Program Files\\Git\\cmd;C:\\Users\\User\\AppData\\Local\\Programs\\oh-my-posh\\bin\\;C:\\Users\\User\\.local\\bin;C:\\Users\\User\\AppData\\Local\\Programs\\Ollama;C:\\Users\\User\\Downloads\\vcmake\\vcpkg\\installed\\x64_windows;C:\\Users\\User\\.cargo\\bin;C:\\Program Files\\OpenSSL\\bin;C:\\Users\\User\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Program Files\\Azure Data Studio\\bin;C:\\Program Files\\PostgreSQL\\15\\bin;C:\\Users\\User\\AppData\\Local\\GitHubDesktop\\bin;C:\\Users\\User\\Downloads\\ffmpeg-master-latest-win64-gpl\\ffmpeg-master-latest-win64-gpl\\bin;C:\\Program Files\\Graphviz\\bin;c:\\Program Files\\zig;c:\\users\\user\\.local\\bin;C:\\Program Files (x86)\\Intel\\oneAPI;C:\\Users\\User\\go\\bin;C:\\Users\\User\\.lmstudio\\bin;C:\\Users\\User\\.dotnet\\tools;C:\\Users\\User\\AppData\\Local\\Programs\\Windsurf\\bin;C:\\Users\\User\\AppData\\Local\\reflex\\bun\\bin;C:\\Users\\User\\AppData\\Local\\Programs\\MiKTeX\\miktex\\bin\\x64\\;C:\\Users\\User\\AppData\\Roaming\\npm;C:\\Users\\User\\go\\bin;C:\\Users\\User\\AppData\\Local\\PowerToys\\" OLLAMA_LIBRARY_PATH=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12
time=2025-11-04T20:36:05.911-05:00 level=INFO source=runner.go:1349 msg="starting ollama engine"
time=2025-11-04T20:36:05.915-05:00 level=INFO source=runner.go:1384 msg="Server listening on 127.0.0.1:65308"
time=2025-11-04T20:36:05.926-05:00 level=DEBUG source=gguf.go:590 msg=general.architecture type=string
time=2025-11-04T20:36:05.928-05:00 level=DEBUG source=gguf.go:590 msg=tokenizer.ggml.model type=string
time=2025-11-04T20:36:05.929-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32
time=2025-11-04T20:36:05.944-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32
time=2025-11-04T20:36:05.944-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.file_type default=0
time=2025-11-04T20:36:05.945-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.name default=""
time=2025-11-04T20:36:05.945-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.description default=""
time=2025-11-04T20:36:05.945-05:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
time=2025-11-04T20:36:05.946-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama
load_backend: loaded CPU backend from C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll
time=2025-11-04T20:36:06.849-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12
time=2025-11-04T20:36:35.728-05:00 level=INFO source=runner.go:498 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" extra_envs=map[] error="failed to finish discovery before timeout"
time=2025-11-04T20:36:35.729-05:00 level=TRACE source=runner.go:501 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" devices=[]
time=2025-11-04T20:36:35.729-05:00 level=DEBUG source=runner.go:471 msg="bootstrap discovery took" duration=30.0029573s OLLAMA_LIBRARY_PATH="[C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" extra_envs=map[]
time=2025-11-04T20:36:35.729-05:00 level=TRACE source=runner.go:474 msg="starting runner for device discovery" libDirs="[C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]" extraEnvs=map[]
time=2025-11-04T20:36:35.751-05:00 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 65322"
time=2025-11-04T20:36:35.751-05:00 level=DEBUG source=server.go:401 msg=subprocess OLLAMA_AUTO_UPDATE=false OLLAMA_DEBUG=2 OLLAMA_MODELS=G:\OllamaFiles\models OLLAMA_RAGTEMP=C:\OllamaRAGTemp PATH="C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13;C:\\Program Files\\PowerShell\\7;C:\\Program Files (x86)\\oh-my-posh\\bin\\;C:\\Users\\User\\Downloads\\vcmake\\vcpkg\\installed\\x64_windows;C:\\Program Files\\Common Files\\Oracle\\Java\\javapath;C:\\ActiveTcl\\bin;C:\\Program Files\\Microsoft MPI\\Bin\\;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314\\Scripts;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314\\tct\\tcl8.6;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314\\tcl;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313\\Scripts;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313\\tcl\\tcl8.6;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313\\tcl;C:\\Program Files\\OpenSSL\\bin;C:\\Users\\User\\AppData\\Roaming\\ActiveState\\bin;C:\\Windows\\system32;C:\\Windows;C:\\Windows\\System32\\Wbem;C:\\Windows\\System32\\WindowsPowerShell\\v1.0\\;C:\\Program Files\\Graphviz\\bin;C:\\Windows\\System32\\OpenSSH\\;C:\\Program Files\\Microsoft SQL Server\\130\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\170\\Tools\\Binn\\;C:\\Program Files\\dotnet\\;C:\\Program Files\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\150\\DTS\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\150\\DTS\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files\\Azure Data Studio\\bin;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\ProgramData\\chocolatey\\bin;C:\\Program Files\\Java\\jdk-21\\bin;C:\\Program Files\\NASM;C:\\Program Files\\Microsoft VS Code\\bin;C:\\Program Files\\gs\\gs10.03.0\\bin;C:\\Program Files (x86)\\Microsoft SQL Server\\160\\DTS\\Binn\\;C:\\Program Files\\PuTTY\\;C:\\Program Files\\RedHat\\Podman\\;C:\\TDM-GCC-64\\bin;D:\\home\\blt\\github\\vcpkg;C:\\Program Files\\CMake\\bin;C:\\Program Files\\nodejs\\;C:\\Program Files\\Go\\bin;C:\\Program Files\\Pandoc\\;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\Program Files\\PowerShell\\7\\;C:\\Program Files (x86)\\Windows Kits\\10\\Windows Performance Toolkit\\;C:\\Program Files\\Git\\cmd;C:\\Users\\User\\AppData\\Local\\Programs\\oh-my-posh\\bin\\;C:\\Users\\User\\.local\\bin;C:\\Users\\User\\AppData\\Local\\Programs\\Ollama;C:\\Users\\User\\Downloads\\vcmake\\vcpkg\\installed\\x64_windows;C:\\Users\\User\\.cargo\\bin;C:\\Program Files\\OpenSSL\\bin;C:\\Users\\User\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Program Files\\Azure Data Studio\\bin;C:\\Program Files\\PostgreSQL\\15\\bin;C:\\Users\\User\\AppData\\Local\\GitHubDesktop\\bin;C:\\Users\\User\\Downloads\\ffmpeg-master-latest-win64-gpl\\ffmpeg-master-latest-win64-gpl\\bin;C:\\Program Files\\Graphviz\\bin;c:\\Program Files\\zig;c:\\users\\user\\.local\\bin;C:\\Program Files (x86)\\Intel\\oneAPI;C:\\Users\\User\\go\\bin;C:\\Users\\User\\.lmstudio\\bin;C:\\Users\\User\\.dotnet\\tools;C:\\Users\\User\\AppData\\Local\\Programs\\Windsurf\\bin;C:\\Users\\User\\AppData\\Local\\reflex\\bun\\bin;C:\\Users\\User\\AppData\\Local\\Programs\\MiKTeX\\miktex\\bin\\x64\\;C:\\Users\\User\\AppData\\Roaming\\npm;C:\\Users\\User\\go\\bin;C:\\Users\\User\\AppData\\Local\\PowerToys\\" OLLAMA_LIBRARY_PATH=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13
time=2025-11-04T20:36:35.970-05:00 level=INFO source=runner.go:1349 msg="starting ollama engine"
time=2025-11-04T20:36:35.973-05:00 level=INFO source=runner.go:1384 msg="Server listening on 127.0.0.1:65322"
time=2025-11-04T20:36:35.976-05:00 level=DEBUG source=gguf.go:590 msg=general.architecture type=string
time=2025-11-04T20:36:35.976-05:00 level=DEBUG source=gguf.go:590 msg=tokenizer.ggml.model type=string
time=2025-11-04T20:36:35.976-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32
time=2025-11-04T20:36:35.982-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32
time=2025-11-04T20:36:35.982-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.file_type default=0
time=2025-11-04T20:36:35.982-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.name default=""
time=2025-11-04T20:36:35.982-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.description default=""
time=2025-11-04T20:36:35.982-05:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
time=2025-11-04T20:36:35.982-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama
load_backend: loaded CPU backend from C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll
time=2025-11-04T20:36:36.072-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13
ggml_cuda_init: failed to initialize CUDA: (null)
load_backend: loaded CUDA backend from C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13\ggml-cuda.dll
time=2025-11-04T20:36:38.318-05:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(clang)
time=2025-11-04T20:36:38.321-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.block_count default=0
time=2025-11-04T20:36:38.324-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.pooling_type default=0
time=2025-11-04T20:36:38.325-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.expert_count default=0
time=2025-11-04T20:36:38.325-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}"
time=2025-11-04T20:36:38.327-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}"
time=2025-11-04T20:36:38.327-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}"
time=2025-11-04T20:36:38.327-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}"
time=2025-11-04T20:36:38.327-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true
time=2025-11-04T20:36:38.327-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
time=2025-11-04T20:36:38.327-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false
time=2025-11-04T20:36:38.327-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0
time=2025-11-04T20:36:38.327-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}"
time=2025-11-04T20:36:38.327-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.pre default=""
time=2025-11-04T20:36:38.329-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.block_count default=0
time=2025-11-04T20:36:38.330-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.embedding_length default=0
time=2025-11-04T20:36:38.330-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.head_count default=0
time=2025-11-04T20:36:38.330-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.head_count_kv default=0
time=2025-11-04T20:36:38.330-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.key_length default=0
time=2025-11-04T20:36:38.330-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.rope.dimension_count default=0
time=2025-11-04T20:36:38.330-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0
time=2025-11-04T20:36:38.330-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.rope.freq_base default=100000
time=2025-11-04T20:36:38.330-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.rope.scaling.factor default=1
time=2025-11-04T20:36:38.333-05:00 level=DEBUG source=runner.go:1324 msg="dummy model load took" duration=2.3568036s
time=2025-11-04T20:36:38.333-05:00 level=DEBUG source=runner.go:1329 msg="gathering device infos took" duration=0s
time=2025-11-04T20:36:38.342-05:00 level=TRACE source=runner.go:501 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]" devices=[]
time=2025-11-04T20:36:38.343-05:00 level=DEBUG source=runner.go:471 msg="bootstrap discovery took" duration=2.6138919s OLLAMA_LIBRARY_PATH="[C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]" extra_envs=map[]
time=2025-11-04T20:36:38.343-05:00 level=TRACE source=runner.go:474 msg="starting runner for device discovery" libDirs="[C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm]" extraEnvs=map[]
time=2025-11-04T20:36:38.351-05:00 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 65337"
time=2025-11-04T20:36:38.351-05:00 level=DEBUG source=server.go:401 msg=subprocess OLLAMA_AUTO_UPDATE=false OLLAMA_DEBUG=2 OLLAMA_MODELS=G:\OllamaFiles\models OLLAMA_RAGTEMP=C:\OllamaRAGTemp PATH="C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm;C:\\Program Files\\PowerShell\\7;C:\\Program Files (x86)\\oh-my-posh\\bin\\;C:\\Users\\User\\Downloads\\vcmake\\vcpkg\\installed\\x64_windows;C:\\Program Files\\Common Files\\Oracle\\Java\\javapath;C:\\ActiveTcl\\bin;C:\\Program Files\\Microsoft MPI\\Bin\\;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314\\Scripts;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314\\tct\\tcl8.6;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314\\tcl;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313\\Scripts;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313\\tcl\\tcl8.6;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313\\tcl;C:\\Program Files\\OpenSSL\\bin;C:\\Users\\User\\AppData\\Roaming\\ActiveState\\bin;C:\\Windows\\system32;C:\\Windows;C:\\Windows\\System32\\Wbem;C:\\Windows\\System32\\WindowsPowerShell\\v1.0\\;C:\\Program Files\\Graphviz\\bin;C:\\Windows\\System32\\OpenSSH\\;C:\\Program Files\\Microsoft SQL Server\\130\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\170\\Tools\\Binn\\;C:\\Program Files\\dotnet\\;C:\\Program Files\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\150\\DTS\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\150\\DTS\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files\\Azure Data Studio\\bin;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\ProgramData\\chocolatey\\bin;C:\\Program Files\\Java\\jdk-21\\bin;C:\\Program Files\\NASM;C:\\Program Files\\Microsoft VS Code\\bin;C:\\Program Files\\gs\\gs10.03.0\\bin;C:\\Program Files (x86)\\Microsoft SQL Server\\160\\DTS\\Binn\\;C:\\Program Files\\PuTTY\\;C:\\Program Files\\RedHat\\Podman\\;C:\\TDM-GCC-64\\bin;D:\\home\\blt\\github\\vcpkg;C:\\Program Files\\CMake\\bin;C:\\Program Files\\nodejs\\;C:\\Program Files\\Go\\bin;C:\\Program Files\\Pandoc\\;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\Program Files\\PowerShell\\7\\;C:\\Program Files (x86)\\Windows Kits\\10\\Windows Performance Toolkit\\;C:\\Program Files\\Git\\cmd;C:\\Users\\User\\AppData\\Local\\Programs\\oh-my-posh\\bin\\;C:\\Users\\User\\.local\\bin;C:\\Users\\User\\AppData\\Local\\Programs\\Ollama;C:\\Users\\User\\Downloads\\vcmake\\vcpkg\\installed\\x64_windows;C:\\Users\\User\\.cargo\\bin;C:\\Program Files\\OpenSSL\\bin;C:\\Users\\User\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Program Files\\Azure Data Studio\\bin;C:\\Program Files\\PostgreSQL\\15\\bin;C:\\Users\\User\\AppData\\Local\\GitHubDesktop\\bin;C:\\Users\\User\\Downloads\\ffmpeg-master-latest-win64-gpl\\ffmpeg-master-latest-win64-gpl\\bin;C:\\Program Files\\Graphviz\\bin;c:\\Program Files\\zig;c:\\users\\user\\.local\\bin;C:\\Program Files (x86)\\Intel\\oneAPI;C:\\Users\\User\\go\\bin;C:\\Users\\User\\.lmstudio\\bin;C:\\Users\\User\\.dotnet\\tools;C:\\Users\\User\\AppData\\Local\\Programs\\Windsurf\\bin;C:\\Users\\User\\AppData\\Local\\reflex\\bun\\bin;C:\\Users\\User\\AppData\\Local\\Programs\\MiKTeX\\miktex\\bin\\x64\\;C:\\Users\\User\\AppData\\Roaming\\npm;C:\\Users\\User\\go\\bin;C:\\Users\\User\\AppData\\Local\\PowerToys\\" OLLAMA_LIBRARY_PATH=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\rocm
time=2025-11-04T20:36:38.601-05:00 level=INFO source=runner.go:1349 msg="starting ollama engine"
time=2025-11-04T20:36:38.604-05:00 level=INFO source=runner.go:1384 msg="Server listening on 127.0.0.1:65337"
time=2025-11-04T20:36:38.608-05:00 level=DEBUG source=gguf.go:590 msg=general.architecture type=string
time=2025-11-04T20:36:38.608-05:00 level=DEBUG source=gguf.go:590 msg=tokenizer.ggml.model type=string
time=2025-11-04T20:36:38.608-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32
time=2025-11-04T20:36:38.611-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32
time=2025-11-04T20:36:38.611-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.file_type default=0
time=2025-11-04T20:36:38.611-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.name default=""
time=2025-11-04T20:36:38.611-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.description default=""
time=2025-11-04T20:36:38.611-05:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
time=2025-11-04T20:36:38.611-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama
load_backend: loaded CPU backend from C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll
time=2025-11-04T20:36:38.661-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\rocm
ggml_cuda_init: failed to initialize ROCm: no ROCm-capable device is detected
load_backend: loaded ROCm backend from C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\rocm\ggml-hip.dll
time=2025-11-04T20:36:39.604-05:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(clang)
time=2025-11-04T20:36:39.604-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.block_count default=0
time=2025-11-04T20:36:39.604-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.pooling_type default=0
time=2025-11-04T20:36:39.604-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.expert_count default=0
time=2025-11-04T20:36:39.604-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}"
time=2025-11-04T20:36:39.604-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}"
time=2025-11-04T20:36:39.604-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}"
time=2025-11-04T20:36:39.604-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}"
time=2025-11-04T20:36:39.604-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true
time=2025-11-04T20:36:39.604-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
time=2025-11-04T20:36:39.604-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false
time=2025-11-04T20:36:39.604-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0
time=2025-11-04T20:36:39.604-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}"
time=2025-11-04T20:36:39.604-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.pre default=""
time=2025-11-04T20:36:39.605-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.block_count default=0
time=2025-11-04T20:36:39.605-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.embedding_length default=0
time=2025-11-04T20:36:39.605-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.head_count default=0
time=2025-11-04T20:36:39.605-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.head_count_kv default=0
time=2025-11-04T20:36:39.605-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.key_length default=0
time=2025-11-04T20:36:39.605-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.rope.dimension_count default=0
time=2025-11-04T20:36:39.605-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0
time=2025-11-04T20:36:39.605-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.rope.freq_base default=100000
time=2025-11-04T20:36:39.605-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.rope.scaling.factor default=1
time=2025-11-04T20:36:39.605-05:00 level=DEBUG source=runner.go:1324 msg="dummy model load took" duration=998.0417ms
time=2025-11-04T20:36:39.605-05:00 level=DEBUG source=runner.go:1329 msg="gathering device infos took" duration=0s
time=2025-11-04T20:36:39.606-05:00 level=TRACE source=runner.go:501 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm]" devices=[]
time=2025-11-04T20:36:39.607-05:00 level=DEBUG source=runner.go:471 msg="bootstrap discovery took" duration=1.263995s OLLAMA_LIBRARY_PATH="[C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm]" extra_envs=map[]
time=2025-11-04T20:36:39.607-05:00 level=DEBUG source=runner.go:120 msg="evluating which if any devices to filter out" initial_count=0
time=2025-11-04T20:36:39.608-05:00 level=TRACE source=runner.go:179 msg="supported GPU library combinations before filtering" supported=map[]
time=2025-11-04T20:36:39.611-05:00 level=DEBUG source=runner.go:41 msg="GPU bootstrap discovery took" duration=33.8889696s
time=2025-11-04T20:36:39.616-05:00 level=INFO source=types.go:60 msg="inference compute" id=cpu library=cpu compute="" name=cpu description=cpu libdirs=ollama driver="" pci_id="" type="" total="11.9 GiB" available="587.9 MiB"
time=2025-11-04T20:36:39.616-05:00 level=INFO source=routes.go:1618 msg="entering low vram mode" "total vram"="0 B" threshold="20.0 GiB"
[GIN] 2025/11/04 - 20:37:08 | 200 |      5.3166ms |       127.0.0.1 | HEAD     "/"
time=2025-11-04T20:37:09.444-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32
[GIN] 2025/11/04 - 20:37:09 | 200 |    1.2758634s |       127.0.0.1 | POST     "/api/show"
time=2025-11-04T20:37:09.876-05:00 level=DEBUG source=runner.go:267 msg="refreshing free memory"
time=2025-11-04T20:37:09.877-05:00 level=DEBUG source=runner.go:41 msg="overall device VRAM discovery took" duration=567.7┬╡s

I hope that helps.

<!-- gh-comment-id:3488760772 --> @katmandoo212 commented on GitHub (Nov 5, 2025): Here is my server log from the latest run using your instructions. ``` $env:OLLAMA_DEBUG="2" ollama serve 2>&1 | % ToString | tee-object serve.log ``` ``` ollama run qwen3:1.7b hello ``` ``` ❯ ollama serve 2>&1 | % ToString | tee-object serve.log time=2025-11-04T20:36:02.700-05:00 level=INFO source=routes.go:1524 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:DEBUG-4 OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:G:\\OllamaFiles\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]" time=2025-11-04T20:36:05.637-05:00 level=INFO source=images.go:522 msg="total blobs: 374" time=2025-11-04T20:36:05.687-05:00 level=INFO source=images.go:529 msg="total unused blobs removed: 0" time=2025-11-04T20:36:05.719-05:00 level=INFO source=routes.go:1577 msg="Listening on 127.0.0.1:11434 (version 0.12.9)" time=2025-11-04T20:36:05.719-05:00 level=DEBUG source=sched.go:120 msg="starting llm scheduler" time=2025-11-04T20:36:05.726-05:00 level=INFO source=runner.go:76 msg="discovering available GPUs..." time=2025-11-04T20:36:05.726-05:00 level=TRACE source=runner.go:474 msg="starting runner for device discovery" libDirs="[C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" extraEnvs=map[] time=2025-11-04T20:36:05.775-05:00 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 65308" time=2025-11-04T20:36:05.775-05:00 level=DEBUG source=server.go:401 msg=subprocess OLLAMA_AUTO_UPDATE=false OLLAMA_DEBUG=2 OLLAMA_MODELS=G:\OllamaFiles\models OLLAMA_RAGTEMP=C:\OllamaRAGTemp PATH="C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12;C:\\Program Files\\PowerShell\\7;C:\\Program Files (x86)\\oh-my-posh\\bin\\;C:\\Users\\User\\Downloads\\vcmake\\vcpkg\\installed\\x64_windows;C:\\Program Files\\Common Files\\Oracle\\Java\\javapath;C:\\ActiveTcl\\bin;C:\\Program Files\\Microsoft MPI\\Bin\\;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314\\Scripts;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314\\tct\\tcl8.6;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314\\tcl;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313\\Scripts;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313\\tcl\\tcl8.6;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313\\tcl;C:\\Program Files\\OpenSSL\\bin;C:\\Users\\User\\AppData\\Roaming\\ActiveState\\bin;C:\\Windows\\system32;C:\\Windows;C:\\Windows\\System32\\Wbem;C:\\Windows\\System32\\WindowsPowerShell\\v1.0\\;C:\\Program Files\\Graphviz\\bin;C:\\Windows\\System32\\OpenSSH\\;C:\\Program Files\\Microsoft SQL Server\\130\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\170\\Tools\\Binn\\;C:\\Program Files\\dotnet\\;C:\\Program Files\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\150\\DTS\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\150\\DTS\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files\\Azure Data Studio\\bin;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\ProgramData\\chocolatey\\bin;C:\\Program Files\\Java\\jdk-21\\bin;C:\\Program Files\\NASM;C:\\Program Files\\Microsoft VS Code\\bin;C:\\Program Files\\gs\\gs10.03.0\\bin;C:\\Program Files (x86)\\Microsoft SQL Server\\160\\DTS\\Binn\\;C:\\Program Files\\PuTTY\\;C:\\Program Files\\RedHat\\Podman\\;C:\\TDM-GCC-64\\bin;D:\\home\\blt\\github\\vcpkg;C:\\Program Files\\CMake\\bin;C:\\Program Files\\nodejs\\;C:\\Program Files\\Go\\bin;C:\\Program Files\\Pandoc\\;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\Program Files\\PowerShell\\7\\;C:\\Program Files (x86)\\Windows Kits\\10\\Windows Performance Toolkit\\;C:\\Program Files\\Git\\cmd;C:\\Users\\User\\AppData\\Local\\Programs\\oh-my-posh\\bin\\;C:\\Users\\User\\.local\\bin;C:\\Users\\User\\AppData\\Local\\Programs\\Ollama;C:\\Users\\User\\Downloads\\vcmake\\vcpkg\\installed\\x64_windows;C:\\Users\\User\\.cargo\\bin;C:\\Program Files\\OpenSSL\\bin;C:\\Users\\User\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Program Files\\Azure Data Studio\\bin;C:\\Program Files\\PostgreSQL\\15\\bin;C:\\Users\\User\\AppData\\Local\\GitHubDesktop\\bin;C:\\Users\\User\\Downloads\\ffmpeg-master-latest-win64-gpl\\ffmpeg-master-latest-win64-gpl\\bin;C:\\Program Files\\Graphviz\\bin;c:\\Program Files\\zig;c:\\users\\user\\.local\\bin;C:\\Program Files (x86)\\Intel\\oneAPI;C:\\Users\\User\\go\\bin;C:\\Users\\User\\.lmstudio\\bin;C:\\Users\\User\\.dotnet\\tools;C:\\Users\\User\\AppData\\Local\\Programs\\Windsurf\\bin;C:\\Users\\User\\AppData\\Local\\reflex\\bun\\bin;C:\\Users\\User\\AppData\\Local\\Programs\\MiKTeX\\miktex\\bin\\x64\\;C:\\Users\\User\\AppData\\Roaming\\npm;C:\\Users\\User\\go\\bin;C:\\Users\\User\\AppData\\Local\\PowerToys\\" OLLAMA_LIBRARY_PATH=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12 time=2025-11-04T20:36:05.911-05:00 level=INFO source=runner.go:1349 msg="starting ollama engine" time=2025-11-04T20:36:05.915-05:00 level=INFO source=runner.go:1384 msg="Server listening on 127.0.0.1:65308" time=2025-11-04T20:36:05.926-05:00 level=DEBUG source=gguf.go:590 msg=general.architecture type=string time=2025-11-04T20:36:05.928-05:00 level=DEBUG source=gguf.go:590 msg=tokenizer.ggml.model type=string time=2025-11-04T20:36:05.929-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32 time=2025-11-04T20:36:05.944-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32 time=2025-11-04T20:36:05.944-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.file_type default=0 time=2025-11-04T20:36:05.945-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.name default="" time=2025-11-04T20:36:05.945-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.description default="" time=2025-11-04T20:36:05.945-05:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3 time=2025-11-04T20:36:05.946-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama load_backend: loaded CPU backend from C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll time=2025-11-04T20:36:06.849-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12 time=2025-11-04T20:36:35.728-05:00 level=INFO source=runner.go:498 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" extra_envs=map[] error="failed to finish discovery before timeout" time=2025-11-04T20:36:35.729-05:00 level=TRACE source=runner.go:501 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" devices=[] time=2025-11-04T20:36:35.729-05:00 level=DEBUG source=runner.go:471 msg="bootstrap discovery took" duration=30.0029573s OLLAMA_LIBRARY_PATH="[C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" extra_envs=map[] time=2025-11-04T20:36:35.729-05:00 level=TRACE source=runner.go:474 msg="starting runner for device discovery" libDirs="[C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]" extraEnvs=map[] time=2025-11-04T20:36:35.751-05:00 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 65322" time=2025-11-04T20:36:35.751-05:00 level=DEBUG source=server.go:401 msg=subprocess OLLAMA_AUTO_UPDATE=false OLLAMA_DEBUG=2 OLLAMA_MODELS=G:\OllamaFiles\models OLLAMA_RAGTEMP=C:\OllamaRAGTemp PATH="C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13;C:\\Program Files\\PowerShell\\7;C:\\Program Files (x86)\\oh-my-posh\\bin\\;C:\\Users\\User\\Downloads\\vcmake\\vcpkg\\installed\\x64_windows;C:\\Program Files\\Common Files\\Oracle\\Java\\javapath;C:\\ActiveTcl\\bin;C:\\Program Files\\Microsoft MPI\\Bin\\;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314\\Scripts;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314\\tct\\tcl8.6;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314\\tcl;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313\\Scripts;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313\\tcl\\tcl8.6;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313\\tcl;C:\\Program Files\\OpenSSL\\bin;C:\\Users\\User\\AppData\\Roaming\\ActiveState\\bin;C:\\Windows\\system32;C:\\Windows;C:\\Windows\\System32\\Wbem;C:\\Windows\\System32\\WindowsPowerShell\\v1.0\\;C:\\Program Files\\Graphviz\\bin;C:\\Windows\\System32\\OpenSSH\\;C:\\Program Files\\Microsoft SQL Server\\130\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\170\\Tools\\Binn\\;C:\\Program Files\\dotnet\\;C:\\Program Files\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\150\\DTS\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\150\\DTS\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files\\Azure Data Studio\\bin;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\ProgramData\\chocolatey\\bin;C:\\Program Files\\Java\\jdk-21\\bin;C:\\Program Files\\NASM;C:\\Program Files\\Microsoft VS Code\\bin;C:\\Program Files\\gs\\gs10.03.0\\bin;C:\\Program Files (x86)\\Microsoft SQL Server\\160\\DTS\\Binn\\;C:\\Program Files\\PuTTY\\;C:\\Program Files\\RedHat\\Podman\\;C:\\TDM-GCC-64\\bin;D:\\home\\blt\\github\\vcpkg;C:\\Program Files\\CMake\\bin;C:\\Program Files\\nodejs\\;C:\\Program Files\\Go\\bin;C:\\Program Files\\Pandoc\\;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\Program Files\\PowerShell\\7\\;C:\\Program Files (x86)\\Windows Kits\\10\\Windows Performance Toolkit\\;C:\\Program Files\\Git\\cmd;C:\\Users\\User\\AppData\\Local\\Programs\\oh-my-posh\\bin\\;C:\\Users\\User\\.local\\bin;C:\\Users\\User\\AppData\\Local\\Programs\\Ollama;C:\\Users\\User\\Downloads\\vcmake\\vcpkg\\installed\\x64_windows;C:\\Users\\User\\.cargo\\bin;C:\\Program Files\\OpenSSL\\bin;C:\\Users\\User\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Program Files\\Azure Data Studio\\bin;C:\\Program Files\\PostgreSQL\\15\\bin;C:\\Users\\User\\AppData\\Local\\GitHubDesktop\\bin;C:\\Users\\User\\Downloads\\ffmpeg-master-latest-win64-gpl\\ffmpeg-master-latest-win64-gpl\\bin;C:\\Program Files\\Graphviz\\bin;c:\\Program Files\\zig;c:\\users\\user\\.local\\bin;C:\\Program Files (x86)\\Intel\\oneAPI;C:\\Users\\User\\go\\bin;C:\\Users\\User\\.lmstudio\\bin;C:\\Users\\User\\.dotnet\\tools;C:\\Users\\User\\AppData\\Local\\Programs\\Windsurf\\bin;C:\\Users\\User\\AppData\\Local\\reflex\\bun\\bin;C:\\Users\\User\\AppData\\Local\\Programs\\MiKTeX\\miktex\\bin\\x64\\;C:\\Users\\User\\AppData\\Roaming\\npm;C:\\Users\\User\\go\\bin;C:\\Users\\User\\AppData\\Local\\PowerToys\\" OLLAMA_LIBRARY_PATH=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13 time=2025-11-04T20:36:35.970-05:00 level=INFO source=runner.go:1349 msg="starting ollama engine" time=2025-11-04T20:36:35.973-05:00 level=INFO source=runner.go:1384 msg="Server listening on 127.0.0.1:65322" time=2025-11-04T20:36:35.976-05:00 level=DEBUG source=gguf.go:590 msg=general.architecture type=string time=2025-11-04T20:36:35.976-05:00 level=DEBUG source=gguf.go:590 msg=tokenizer.ggml.model type=string time=2025-11-04T20:36:35.976-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32 time=2025-11-04T20:36:35.982-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32 time=2025-11-04T20:36:35.982-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.file_type default=0 time=2025-11-04T20:36:35.982-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.name default="" time=2025-11-04T20:36:35.982-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.description default="" time=2025-11-04T20:36:35.982-05:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3 time=2025-11-04T20:36:35.982-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama load_backend: loaded CPU backend from C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll time=2025-11-04T20:36:36.072-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13 ggml_cuda_init: failed to initialize CUDA: (null) load_backend: loaded CUDA backend from C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13\ggml-cuda.dll time=2025-11-04T20:36:38.318-05:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(clang) time=2025-11-04T20:36:38.321-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.block_count default=0 time=2025-11-04T20:36:38.324-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.pooling_type default=0 time=2025-11-04T20:36:38.325-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.expert_count default=0 time=2025-11-04T20:36:38.325-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}" time=2025-11-04T20:36:38.327-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}" time=2025-11-04T20:36:38.327-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}" time=2025-11-04T20:36:38.327-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}" time=2025-11-04T20:36:38.327-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true time=2025-11-04T20:36:38.327-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0 time=2025-11-04T20:36:38.327-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false time=2025-11-04T20:36:38.327-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0 time=2025-11-04T20:36:38.327-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}" time=2025-11-04T20:36:38.327-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.pre default="" time=2025-11-04T20:36:38.329-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.block_count default=0 time=2025-11-04T20:36:38.330-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.embedding_length default=0 time=2025-11-04T20:36:38.330-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.head_count default=0 time=2025-11-04T20:36:38.330-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.head_count_kv default=0 time=2025-11-04T20:36:38.330-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.key_length default=0 time=2025-11-04T20:36:38.330-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.rope.dimension_count default=0 time=2025-11-04T20:36:38.330-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0 time=2025-11-04T20:36:38.330-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.rope.freq_base default=100000 time=2025-11-04T20:36:38.330-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.rope.scaling.factor default=1 time=2025-11-04T20:36:38.333-05:00 level=DEBUG source=runner.go:1324 msg="dummy model load took" duration=2.3568036s time=2025-11-04T20:36:38.333-05:00 level=DEBUG source=runner.go:1329 msg="gathering device infos took" duration=0s time=2025-11-04T20:36:38.342-05:00 level=TRACE source=runner.go:501 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]" devices=[] time=2025-11-04T20:36:38.343-05:00 level=DEBUG source=runner.go:471 msg="bootstrap discovery took" duration=2.6138919s OLLAMA_LIBRARY_PATH="[C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]" extra_envs=map[] time=2025-11-04T20:36:38.343-05:00 level=TRACE source=runner.go:474 msg="starting runner for device discovery" libDirs="[C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm]" extraEnvs=map[] time=2025-11-04T20:36:38.351-05:00 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 65337" time=2025-11-04T20:36:38.351-05:00 level=DEBUG source=server.go:401 msg=subprocess OLLAMA_AUTO_UPDATE=false OLLAMA_DEBUG=2 OLLAMA_MODELS=G:\OllamaFiles\models OLLAMA_RAGTEMP=C:\OllamaRAGTemp PATH="C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm;C:\\Program Files\\PowerShell\\7;C:\\Program Files (x86)\\oh-my-posh\\bin\\;C:\\Users\\User\\Downloads\\vcmake\\vcpkg\\installed\\x64_windows;C:\\Program Files\\Common Files\\Oracle\\Java\\javapath;C:\\ActiveTcl\\bin;C:\\Program Files\\Microsoft MPI\\Bin\\;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314\\Scripts;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314\\tct\\tcl8.6;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python314\\tcl;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313\\Scripts;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313\\tcl\\tcl8.6;C:\\Users\\User\\AppData\\Local\\Programs\\Python\\Python313\\tcl;C:\\Program Files\\OpenSSL\\bin;C:\\Users\\User\\AppData\\Roaming\\ActiveState\\bin;C:\\Windows\\system32;C:\\Windows;C:\\Windows\\System32\\Wbem;C:\\Windows\\System32\\WindowsPowerShell\\v1.0\\;C:\\Program Files\\Graphviz\\bin;C:\\Windows\\System32\\OpenSSH\\;C:\\Program Files\\Microsoft SQL Server\\130\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\170\\Tools\\Binn\\;C:\\Program Files\\dotnet\\;C:\\Program Files\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\150\\DTS\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\150\\DTS\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files\\Azure Data Studio\\bin;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\ProgramData\\chocolatey\\bin;C:\\Program Files\\Java\\jdk-21\\bin;C:\\Program Files\\NASM;C:\\Program Files\\Microsoft VS Code\\bin;C:\\Program Files\\gs\\gs10.03.0\\bin;C:\\Program Files (x86)\\Microsoft SQL Server\\160\\DTS\\Binn\\;C:\\Program Files\\PuTTY\\;C:\\Program Files\\RedHat\\Podman\\;C:\\TDM-GCC-64\\bin;D:\\home\\blt\\github\\vcpkg;C:\\Program Files\\CMake\\bin;C:\\Program Files\\nodejs\\;C:\\Program Files\\Go\\bin;C:\\Program Files\\Pandoc\\;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\Program Files\\PowerShell\\7\\;C:\\Program Files (x86)\\Windows Kits\\10\\Windows Performance Toolkit\\;C:\\Program Files\\Git\\cmd;C:\\Users\\User\\AppData\\Local\\Programs\\oh-my-posh\\bin\\;C:\\Users\\User\\.local\\bin;C:\\Users\\User\\AppData\\Local\\Programs\\Ollama;C:\\Users\\User\\Downloads\\vcmake\\vcpkg\\installed\\x64_windows;C:\\Users\\User\\.cargo\\bin;C:\\Program Files\\OpenSSL\\bin;C:\\Users\\User\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Program Files\\Azure Data Studio\\bin;C:\\Program Files\\PostgreSQL\\15\\bin;C:\\Users\\User\\AppData\\Local\\GitHubDesktop\\bin;C:\\Users\\User\\Downloads\\ffmpeg-master-latest-win64-gpl\\ffmpeg-master-latest-win64-gpl\\bin;C:\\Program Files\\Graphviz\\bin;c:\\Program Files\\zig;c:\\users\\user\\.local\\bin;C:\\Program Files (x86)\\Intel\\oneAPI;C:\\Users\\User\\go\\bin;C:\\Users\\User\\.lmstudio\\bin;C:\\Users\\User\\.dotnet\\tools;C:\\Users\\User\\AppData\\Local\\Programs\\Windsurf\\bin;C:\\Users\\User\\AppData\\Local\\reflex\\bun\\bin;C:\\Users\\User\\AppData\\Local\\Programs\\MiKTeX\\miktex\\bin\\x64\\;C:\\Users\\User\\AppData\\Roaming\\npm;C:\\Users\\User\\go\\bin;C:\\Users\\User\\AppData\\Local\\PowerToys\\" OLLAMA_LIBRARY_PATH=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\rocm time=2025-11-04T20:36:38.601-05:00 level=INFO source=runner.go:1349 msg="starting ollama engine" time=2025-11-04T20:36:38.604-05:00 level=INFO source=runner.go:1384 msg="Server listening on 127.0.0.1:65337" time=2025-11-04T20:36:38.608-05:00 level=DEBUG source=gguf.go:590 msg=general.architecture type=string time=2025-11-04T20:36:38.608-05:00 level=DEBUG source=gguf.go:590 msg=tokenizer.ggml.model type=string time=2025-11-04T20:36:38.608-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32 time=2025-11-04T20:36:38.611-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32 time=2025-11-04T20:36:38.611-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.file_type default=0 time=2025-11-04T20:36:38.611-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.name default="" time=2025-11-04T20:36:38.611-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.description default="" time=2025-11-04T20:36:38.611-05:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3 time=2025-11-04T20:36:38.611-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama load_backend: loaded CPU backend from C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll time=2025-11-04T20:36:38.661-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\rocm ggml_cuda_init: failed to initialize ROCm: no ROCm-capable device is detected load_backend: loaded ROCm backend from C:\Users\User\AppData\Local\Programs\Ollama\lib\ollama\rocm\ggml-hip.dll time=2025-11-04T20:36:39.604-05:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(clang) time=2025-11-04T20:36:39.604-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.block_count default=0 time=2025-11-04T20:36:39.604-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.pooling_type default=0 time=2025-11-04T20:36:39.604-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.expert_count default=0 time=2025-11-04T20:36:39.604-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}" time=2025-11-04T20:36:39.604-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}" time=2025-11-04T20:36:39.604-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}" time=2025-11-04T20:36:39.604-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}" time=2025-11-04T20:36:39.604-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true time=2025-11-04T20:36:39.604-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0 time=2025-11-04T20:36:39.604-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false time=2025-11-04T20:36:39.604-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0 time=2025-11-04T20:36:39.604-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}" time=2025-11-04T20:36:39.604-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=tokenizer.ggml.pre default="" time=2025-11-04T20:36:39.605-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.block_count default=0 time=2025-11-04T20:36:39.605-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.embedding_length default=0 time=2025-11-04T20:36:39.605-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.head_count default=0 time=2025-11-04T20:36:39.605-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.head_count_kv default=0 time=2025-11-04T20:36:39.605-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.key_length default=0 time=2025-11-04T20:36:39.605-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.rope.dimension_count default=0 time=2025-11-04T20:36:39.605-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0 time=2025-11-04T20:36:39.605-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.rope.freq_base default=100000 time=2025-11-04T20:36:39.605-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=llama.rope.scaling.factor default=1 time=2025-11-04T20:36:39.605-05:00 level=DEBUG source=runner.go:1324 msg="dummy model load took" duration=998.0417ms time=2025-11-04T20:36:39.605-05:00 level=DEBUG source=runner.go:1329 msg="gathering device infos took" duration=0s time=2025-11-04T20:36:39.606-05:00 level=TRACE source=runner.go:501 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm]" devices=[] time=2025-11-04T20:36:39.607-05:00 level=DEBUG source=runner.go:471 msg="bootstrap discovery took" duration=1.263995s OLLAMA_LIBRARY_PATH="[C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\User\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm]" extra_envs=map[] time=2025-11-04T20:36:39.607-05:00 level=DEBUG source=runner.go:120 msg="evluating which if any devices to filter out" initial_count=0 time=2025-11-04T20:36:39.608-05:00 level=TRACE source=runner.go:179 msg="supported GPU library combinations before filtering" supported=map[] time=2025-11-04T20:36:39.611-05:00 level=DEBUG source=runner.go:41 msg="GPU bootstrap discovery took" duration=33.8889696s time=2025-11-04T20:36:39.616-05:00 level=INFO source=types.go:60 msg="inference compute" id=cpu library=cpu compute="" name=cpu description=cpu libdirs=ollama driver="" pci_id="" type="" total="11.9 GiB" available="587.9 MiB" time=2025-11-04T20:36:39.616-05:00 level=INFO source=routes.go:1618 msg="entering low vram mode" "total vram"="0 B" threshold="20.0 GiB" [GIN] 2025/11/04 - 20:37:08 | 200 | 5.3166ms | 127.0.0.1 | HEAD "/" time=2025-11-04T20:37:09.444-05:00 level=DEBUG source=ggml.go:276 msg="key with type not found" key=general.alignment default=32 [GIN] 2025/11/04 - 20:37:09 | 200 | 1.2758634s | 127.0.0.1 | POST "/api/show" time=2025-11-04T20:37:09.876-05:00 level=DEBUG source=runner.go:267 msg="refreshing free memory" time=2025-11-04T20:37:09.877-05:00 level=DEBUG source=runner.go:41 msg="overall device VRAM discovery took" duration=567.7┬╡s ``` I hope that helps.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug windows
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#34151
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?