github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #8035] NOT ABLE TO INSTALL "llama 3.2 model" #67195

New Issue
Closed
opened 2026-05-04 09:36:12 -05:00 by GiteaMirror · 7 comments
GiteaMirror commented 2026-05-04 09:36:12 -05:00
Owner
Copy Link

Originally created by @PriyeshGit on GitHub (Dec 11, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/8035

What is the issue?

After installing Ollama on my PC.
When I try to install llama3.2 model.
I always get the same error, but I am not able comprehend what is wrong.

Welcome to Ollama!
Run your first model:
ollama run llama3.2

PS C:\Windows\System32> ollama run llama3.2
Error: something went wrong, please see the ollama server logs for details

Here is how my server log looks like:

2024/12/10 17:17:36 routes.go:1195: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY:https://proxy.example.com:8080 HTTP_PROXY:http://proxy.example.com:8080 NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 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:\Path\To\Models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 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://*] OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]"
time=2024-12-10T17:17:36.214+09:00 level=INFO source=images.go:753 msg="total blobs: 0"
time=2024-12-10T17:17:36.214+09:00 level=INFO source=images.go:760 msg="total unused blobs removed: 0"
time=2024-12-10T17:17:36.218+09:00 level=INFO source=routes.go:1246 msg="Listening on [::]:11434 (version 0.5.1)"
time=2024-12-10T17:17:36.222+09:00 level=INFO source=common.go:49 msg="Dynamic LLM libraries" runners="[rocm cpu cpu_avx cpu_avx2 cuda_v11 cuda_v12]"
time=2024-12-10T17:17:36.222+09:00 level=INFO source=gpu.go:221 msg="looking for compatible GPUs"
time=2024-12-10T17:17:36.223+09:00 level=INFO source=gpu_windows.go:167 msg=packages count=1
time=2024-12-10T17:17:36.223+09:00 level=INFO source=gpu_windows.go:183 msg="efficiency cores detected" maxEfficiencyClass=1
time=2024-12-10T17:17:36.223+09:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=12 efficiency=10 threads=14
time=2024-12-10T17:17:36.246+09:00 level=INFO source=gpu.go:386 msg="no compatible GPUs were discovered"
time=2024-12-10T17:17:36.246+09:00 level=INFO source=types.go:123 msg="inference compute" id=0 library=cpu variant=avx2 compute="" driver=0.0 name="" total="31.5 GiB" available="12.5 GiB"

OS

Windows

GPU

No response

CPU

Intel

Ollama version

No response

Originally created by @PriyeshGit on GitHub (Dec 11, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/8035 ### What is the issue? After installing Ollama on my PC. When I try to install llama3.2 model. I always get the same error, but I am not able comprehend what is wrong. Welcome to Ollama! Run your first model: ollama run llama3.2 PS C:\Windows\System32> ollama run llama3.2 Error: something went wrong, please see the ollama server logs for details **Here is how my server log looks like:** 2024/12/10 17:17:36 routes.go:1195: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY:https://proxy.example.com:8080 HTTP_PROXY:http://proxy.example.com:8080 NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 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:\Path\To\Models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 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://*] OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]" time=2024-12-10T17:17:36.214+09:00 level=INFO source=images.go:753 msg="total blobs: 0" time=2024-12-10T17:17:36.214+09:00 level=INFO source=images.go:760 msg="total unused blobs removed: 0" time=2024-12-10T17:17:36.218+09:00 level=INFO source=routes.go:1246 msg="Listening on [::]:11434 (version 0.5.1)" time=2024-12-10T17:17:36.222+09:00 level=INFO source=common.go:49 msg="Dynamic LLM libraries" runners="[rocm cpu cpu_avx cpu_avx2 cuda_v11 cuda_v12]" time=2024-12-10T17:17:36.222+09:00 level=INFO source=gpu.go:221 msg="looking for compatible GPUs" time=2024-12-10T17:17:36.223+09:00 level=INFO source=gpu_windows.go:167 msg=packages count=1 time=2024-12-10T17:17:36.223+09:00 level=INFO source=gpu_windows.go:183 msg="efficiency cores detected" maxEfficiencyClass=1 time=2024-12-10T17:17:36.223+09:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=12 efficiency=10 threads=14 time=2024-12-10T17:17:36.246+09:00 level=INFO source=gpu.go:386 msg="no compatible GPUs were discovered" time=2024-12-10T17:17:36.246+09:00 level=INFO source=types.go:123 msg="inference compute" id=0 library=cpu variant=avx2 compute="" driver=0.0 name="" total="31.5 GiB" available="12.5 GiB" ### OS Windows ### GPU _No response_ ### CPU Intel ### Ollama version _No response_
GiteaMirror added the bugwindows labels 2026-05-04 09:36:12 -05:00
GiteaMirror commented 2026-05-04 09:36:15 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 11, 2024):

You have HTTP_PROXY set, the client is unable to connect to the server because it's being routed through the proxy. Unset HTTP_PROXY in the client enviromment.

<!-- gh-comment-id:2533376349 --> @rick-github commented on GitHub (Dec 11, 2024): You have `HTTP_PROXY` set, the client is unable to connect to the server because it's being routed through the proxy. Unset `HTTP_PROXY` in the client enviromment.
GiteaMirror commented 2026-05-04 09:36:15 -05:00
Author
Owner
Copy Link

@PriyeshGit commented on GitHub (Dec 11, 2024):

Thank you for your response,
I have unset the HTTP_PROXY, but still the same error is showing up.

C:\Users[USERNAME]>set HTTP_PROXY=

C:\Users[USERNAME]>set HTTPS_PROXY=

C:\Users[USERNAME]>ollama serve
2024/12/11 10:19:37 routes.go:1195: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 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\[USERNAME]\.ollama\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 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://*] OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]"
time=2024-12-11T10:19:37.500+09:00 level=INFO source=images.go:753 msg="total blobs: 0"
time=2024-12-11T10:19:37.506+09:00 level=INFO source=images.go:760 msg="total unused blobs removed: 0"
time=2024-12-11T10:19:37.519+09:00 level=INFO source=routes.go:1246 msg="Listening on [::]:11434 (version 0.5.1)"
time=2024-12-11T10:19:37.537+09:00 level=INFO source=common.go:49 msg="Dynamic LLM libraries" runners="[cpu cpu_avx cpu_avx2 cuda_v11 cuda_v12 rocm]"
time=2024-12-11T10:19:37.538+09:00 level=INFO source=gpu.go:221 msg="looking for compatible GPUs"
time=2024/12/11 10:19:37.539+09:00 level=INFO source=gpu_windows.go:167 msg="packages count=1"
time=2024/12/11 10:19:37.539+09:00 level=INFO source=gpu_windows.go:183 msg="efficiency cores detected" maxEfficiencyClass=1
time=2024/12/11 10:19:37.539+09:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=12 efficiency=10 threads=14
time=2024/12/11 10:19:37.639+09:00 level=INFO source=gpu.go:386 msg="no compatible GPUs were discovered"
time=2024/12/11 10:19:37.640+09:00 level=INFO source=types.go:123 msg="inference compute" id=0 library=cpu variant=avx2 compute="" driver=0.0 name="" total="31.5 GiB" available="16.9 GiB"

C:\Users[USERNAME]>ollama pull llama3.2
Error: something went wrong, please see the ollama server logs for details

<!-- gh-comment-id:2533412172 --> @PriyeshGit commented on GitHub (Dec 11, 2024): Thank you for your response, I have unset the HTTP_PROXY, but still the same error is showing up. C:\Users\[USERNAME]>set HTTP_PROXY= C:\Users\[USERNAME]>set HTTPS_PROXY= C:\Users\[USERNAME]>ollama serve 2024/12/11 10:19:37 routes.go:1195: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 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\\[USERNAME]\\.ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 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://*] OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]" time=2024-12-11T10:19:37.500+09:00 level=INFO source=images.go:753 msg="total blobs: 0" time=2024-12-11T10:19:37.506+09:00 level=INFO source=images.go:760 msg="total unused blobs removed: 0" time=2024-12-11T10:19:37.519+09:00 level=INFO source=routes.go:1246 msg="Listening on [::]:11434 (version 0.5.1)" time=2024-12-11T10:19:37.537+09:00 level=INFO source=common.go:49 msg="Dynamic LLM libraries" runners="[cpu cpu_avx cpu_avx2 cuda_v11 cuda_v12 rocm]" time=2024-12-11T10:19:37.538+09:00 level=INFO source=gpu.go:221 msg="looking for compatible GPUs" time=2024/12/11 10:19:37.539+09:00 level=INFO source=gpu_windows.go:167 msg="packages count=1" time=2024/12/11 10:19:37.539+09:00 level=INFO source=gpu_windows.go:183 msg="efficiency cores detected" maxEfficiencyClass=1 time=2024/12/11 10:19:37.539+09:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=12 efficiency=10 threads=14 time=2024/12/11 10:19:37.639+09:00 level=INFO source=gpu.go:386 msg="no compatible GPUs were discovered" time=2024/12/11 10:19:37.640+09:00 level=INFO source=types.go:123 msg="inference compute" id=0 library=cpu variant=avx2 compute="" driver=0.0 name="" total="31.5 GiB" available="16.9 GiB" C:\Users\[USERNAME]>ollama pull llama3.2 Error: something went wrong, please see the ollama server logs for details
GiteaMirror commented 2026-05-04 09:36:16 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 11, 2024):

You unset HTTP_PROXY in the server environment. You need to unset HTTP_PROXY in the client environment.

C:\Users[USERNAME]>set HTTP_PROXY=
C:\Users[USERNAME]>ollama pull llama3.2
<!-- gh-comment-id:2533416716 --> @rick-github commented on GitHub (Dec 11, 2024): You unset `HTTP_PROXY` in the server environment. You need to unset `HTTP_PROXY` in the client environment. ``` C:\Users[USERNAME]>set HTTP_PROXY= C:\Users[USERNAME]>ollama pull llama3.2 ```
GiteaMirror commented 2026-05-04 09:36:16 -05:00
Author
Owner
Copy Link

@PriyeshGit commented on GitHub (Dec 11, 2024):

Thank you, this time the error was not shown but a new error is emerging.

PS C:\Windows\System32> set HTTP_PROXY=
PS C:\Windows\System32> ollama pull llama3.2
pulling manifest
Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/llama3.2/manifests/latest": dial tcp 104.21.75.227:443: i/o timeout

<!-- gh-comment-id:2533604484 --> @PriyeshGit commented on GitHub (Dec 11, 2024): Thank you, this time the error was not shown but a new error is emerging. PS C:\Windows\System32> set HTTP_PROXY= PS C:\Windows\System32> ollama pull llama3.2 pulling manifest Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/llama3.2/manifests/latest": dial tcp 104.21.75.227:443: i/o timeout
GiteaMirror commented 2026-05-04 09:36:19 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 11, 2024):

You still need to set HTTPS_PROXY in the server environment.

<!-- gh-comment-id:2535445176 --> @rick-github commented on GitHub (Dec 11, 2024): You still need to set `HTTPS_PROXY` in the server environment.
GiteaMirror commented 2026-05-04 09:36:22 -05:00
Author
Owner
Copy Link

@athmanar commented on GitHub (Dec 11, 2024):

hello i can confirm this does not seem to work.. set HTTPS_PROXY on WINDOWS

<!-- gh-comment-id:2536819039 --> @athmanar commented on GitHub (Dec 11, 2024): hello i can confirm this does not seem to work.. set HTTPS_PROXY on WINDOWS
GiteaMirror commented 2026-05-04 09:36:23 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 11, 2024):

socks5 proxy with ollama-0.5.1 works fine.

C:\Users\bill>set https_proxy=socks5://z1:1080
C:\Users\bill>ollama serve
2024/12/11 20:56:53 routes.go:1195: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY:socks5://z1:1080 HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://:11435 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\\bill\\.ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[chrome-extension://* 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://*] OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]"
time=2024-12-11T20:57:07.715-08:00 level=INFO source=images.go:753 msg="total blobs: 10"
time=2024-12-11T20:57:07.721-08:00 level=INFO source=images.go:760 msg="total unused blobs removed: 0"
time=2024-12-11T20:57:07.745-08:00 level=INFO source=routes.go:1246 msg="Listening on [::]:11435 (version 0.5.1)
time=2024-12-11T20:57:07.746-08:00 level=INFO source=common.go:49 msg="Dynamic LLM libraries" runners="[cpu_avx2 cuda_v11 cuda_v12 rocm cpu cpu_avx]"
time=2024-12-11T20:57:07.747-08:00 level=INFO source=gpu.go:221 msg="looking for compatible GPUs"
time=2024-12-11T20:57:07.748-08:00 level=INFO source=gpu_windows.go:167 msg=packages count=1
time=2024-12-11T20:57:07.749-08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=1 efficiency=0 threads=1
time=2024-12-11T20:57:07.782-08:00 level=INFO source=gpu.go:386 msg="no compatible GPUs were discovered"
time=2024-12-11T20:57:07.789-08:00 level=INFO source=types.go:123 msg="inference compute" id=0 library=cpu variant=avx2 compute="" driver=0.0 name="" total="4.0 GiB" available="1.7 GiB"                                                       
[GIN] 2024/12/11 - 20:57:29 | 200 |            0s |       127.0.0.1 | HEAD     "/"                                      
time=2024-12-11T20:57:31.682-08:00 level=INFO source=download.go:175 msg="downloading 74701a8c35f6 in 14 100 MB part(s)"
time=2024-12-11T20:57:55.414-08:00 level=INFO source=download.go:175 msg="downloading 966de95ca8a6 in 1 1.4 KB part(s)"
time=2024-12-11T20:57:56.806-08:00 level=INFO source=download.go:175 msg="downloading fcc5a6bec9da in 1 7.7 KB part(s)"
time=2024-12-11T20:57:58.245-08:00 level=INFO source=download.go:175 msg="downloading a70ff7e570d9 in 1 6.0 KB part(s)" 
time=2024-12-11T20:57:59.624-08:00 level=INFO source=download.go:175 msg="downloading 4f659a1e86d7 in 1 485 B part(s)"  
[GIN] 2024/12/11 - 20:58:08 | 200 |   38.5621367s |       127.0.0.1 | POST     "/api/pull"

If I set the proxy incorrectly, it fails.

C:\Users\bill>set https_proxy=socks5://z1:1081
C:\Users\bill>ollama serve
...
time=2024-12-11T21:07:29.665-08:00 level=INFO source=images.go:990 msg="request failed: Get \"https://registry.ollama.ai/v2/library/llama3.2/manifests/1b\": proxyconnect tcp: dial tcp 10.0.3.1:1081: connectex: No connection could be made because the target machine actively refused it."
[GIN] 2024/12/11 - 21:07:29 | 200 |    2.1723186s |       127.0.0.1 | POST     "/api/pull"

If you could add some details like error message and configuration it would greatly enhance the possibility of diagnosing your problem.

<!-- gh-comment-id:2537195772 --> @rick-github commented on GitHub (Dec 11, 2024): socks5 proxy with ollama-0.5.1 works fine. ```console C:\Users\bill>set https_proxy=socks5://z1:1080 C:\Users\bill>ollama serve 2024/12/11 20:56:53 routes.go:1195: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY:socks5://z1:1080 HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://:11435 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\\bill\\.ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[chrome-extension://* 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://*] OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]" time=2024-12-11T20:57:07.715-08:00 level=INFO source=images.go:753 msg="total blobs: 10" time=2024-12-11T20:57:07.721-08:00 level=INFO source=images.go:760 msg="total unused blobs removed: 0" time=2024-12-11T20:57:07.745-08:00 level=INFO source=routes.go:1246 msg="Listening on [::]:11435 (version 0.5.1) time=2024-12-11T20:57:07.746-08:00 level=INFO source=common.go:49 msg="Dynamic LLM libraries" runners="[cpu_avx2 cuda_v11 cuda_v12 rocm cpu cpu_avx]" time=2024-12-11T20:57:07.747-08:00 level=INFO source=gpu.go:221 msg="looking for compatible GPUs" time=2024-12-11T20:57:07.748-08:00 level=INFO source=gpu_windows.go:167 msg=packages count=1 time=2024-12-11T20:57:07.749-08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=1 efficiency=0 threads=1 time=2024-12-11T20:57:07.782-08:00 level=INFO source=gpu.go:386 msg="no compatible GPUs were discovered" time=2024-12-11T20:57:07.789-08:00 level=INFO source=types.go:123 msg="inference compute" id=0 library=cpu variant=avx2 compute="" driver=0.0 name="" total="4.0 GiB" available="1.7 GiB" [GIN] 2024/12/11 - 20:57:29 | 200 | 0s | 127.0.0.1 | HEAD "/" time=2024-12-11T20:57:31.682-08:00 level=INFO source=download.go:175 msg="downloading 74701a8c35f6 in 14 100 MB part(s)" time=2024-12-11T20:57:55.414-08:00 level=INFO source=download.go:175 msg="downloading 966de95ca8a6 in 1 1.4 KB part(s)" time=2024-12-11T20:57:56.806-08:00 level=INFO source=download.go:175 msg="downloading fcc5a6bec9da in 1 7.7 KB part(s)" time=2024-12-11T20:57:58.245-08:00 level=INFO source=download.go:175 msg="downloading a70ff7e570d9 in 1 6.0 KB part(s)" time=2024-12-11T20:57:59.624-08:00 level=INFO source=download.go:175 msg="downloading 4f659a1e86d7 in 1 485 B part(s)" [GIN] 2024/12/11 - 20:58:08 | 200 | 38.5621367s | 127.0.0.1 | POST "/api/pull" ``` If I set the proxy incorrectly, it fails. ```console C:\Users\bill>set https_proxy=socks5://z1:1081 C:\Users\bill>ollama serve ... time=2024-12-11T21:07:29.665-08:00 level=INFO source=images.go:990 msg="request failed: Get \"https://registry.ollama.ai/v2/library/llama3.2/manifests/1b\": proxyconnect tcp: dial tcp 10.0.3.1:1081: connectex: No connection could be made because the target machine actively refused it." [GIN] 2024/12/11 - 21:07:29 | 200 | 2.1723186s | 127.0.0.1 | POST "/api/pull" ``` If you could add some details like error message and configuration it would greatly enhance the possibility of diagnosing your problem.
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#67195
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?