[GH-ISSUE #15410] 500 Internal Server Error - All freakin models after reboot #71913

New Issue

GiteaMirror · 2026-05-05T02:56:14-05:00

GiteaMirror commented

2026-05-05 02:56:14 -05:00

Originally created by @ch473221 on GitHub (Apr 8, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15410

What is the issue?

Hi all! This has been an issue across all models I've pulled directly from Ollama. I pull them, run them, and they work fine until a restart/reboot. After that, models will run and provide a prompt, but the second I interact with the model, it throws "500 Internal Server Error: model runner has unexpectedly stopped, this may be due to resource limitations or an internal error, check ollama server logs for details." I've spent a day troubleshooting and am stuck. Any help would be greatly appreciated!

4080
64 GB RAM
4TB 5.0 NVME
Windows 11
Models tested: qwen3-vl:4b, qwen35:4b
File hashes are consistent (no corruption)
CPU-only mode produces gibberish after reboot

Relevant log output

Ollama version: 0.20.3
Model path: [REDACTED]

time=... msg="loading model"
time=... msg="starting ollama engine"
time=... msg="Server listening on 127.0.0.1"

time=... msg="llama runner started in ~2 seconds"

panic: failed to sample token

goroutine ... [running]:
github.com/ollama/ollama/runner/ollamarunner.(*Server).computeBatch(...)
    runner.go:762

error="Post \"http://127.0.0.1:PORT/completion\": 
wsarecv: An existing connection was forcibly closed by the remote host."

[GIN] ... | 500 | POST "/api/chat"

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.20.3

Originally created by @ch473221 on GitHub (Apr 8, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15410 ### What is the issue? Hi all! This has been an issue across all models I've pulled directly from Ollama. I pull them, run them, and they work fine until a restart/reboot. After that, models will run and provide a prompt, but the second I interact with the model, it throws "500 Internal Server Error: model runner has unexpectedly stopped, this may be due to resource limitations or an internal error, check ollama server logs for details." I've spent a day troubleshooting and am stuck. Any help would be greatly appreciated! 4080 64 GB RAM 4TB 5.0 NVME Windows 11 Models tested: qwen3-vl:4b, qwen35:4b File hashes are consistent (no corruption) CPU-only mode produces gibberish after reboot ### Relevant log output ```shell Ollama version: 0.20.3 Model path: [REDACTED] time=... msg="loading model" time=... msg="starting ollama engine" time=... msg="Server listening on 127.0.0.1" time=... msg="llama runner started in ~2 seconds" panic: failed to sample token goroutine ... [running]: github.com/ollama/ollama/runner/ollamarunner.(*Server).computeBatch(...) runner.go:762 error="Post \"http://127.0.0.1:PORT/completion\": wsarecv: An existing connection was forcibly closed by the remote host." [GIN] ... | 500 | POST "/api/chat" ``` ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.20.3

GiteaMirror added the bug label 2026-05-05 02:56:14 -05:00

GiteaMirror commented

2026-05-05 02:56:17 -05:00

@rick-github commented on GitHub (Apr 8, 2026):

Server logs will aid in debugging.

@rick-github commented on GitHub (Apr 8, 2026): [Server logs](https://docs.ollama.com/troubleshooting) will aid in debugging.

GiteaMirror commented

2026-05-05 02:56:19 -05:00

@ch473221 commented on GitHub (Apr 8, 2026):

Server logs will aid in debugging.

Here is the latest log...

time=2026-04-07T17:19:19.939-07:00 level=INFO source=routes.go:1744 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:0 OLLAMA_DEBUG:INFO OLLAMA_DEBUG_LOG_REQUESTS:false OLLAMA_EDITOR: OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 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:E:\PATH\TO\MODELS OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NO_CLOUD: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 OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES:]"
time=2026-04-07T17:19:19.939-07:00 level=INFO source=routes.go:1746 msg="Ollama cloud disabled: false"
time=2026-04-07T17:19:19.945-07:00 level=INFO source=images.go:499 msg="total blobs: 7"
time=2026-04-07T17:19:19.946-07:00 level=INFO source=images.go:506 msg="total unused blobs removed: 0"
time=2026-04-07T17:19:19.947-07:00 level=INFO source=routes.go:1802 msg="Listening on 127.0.0.1:11434 (version 0.20.3)"
time=2026-04-07T17:19:19.949-07:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
time=2026-04-07T17:19:19.961-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 51530"
time=2026-04-07T17:19:20.157-07:00 level=INFO source=runner.go:106 msg="experimental Vulkan support disabled. To enable, set OLLAMA_VULKAN=1"
time=2026-04-07T17:19:20.158-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 51542"
time=2026-04-07T17:19:20.543-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 51553"
time=2026-04-07T17:19:20.891-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 51563"
time=2026-04-07T17:19:20.891-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 51564"
time=2026-04-07T17:19:21.122-07:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-REDACTED filter_id="" library=CUDA compute=8.9 name=CUDA0 description="NVIDIA GeForce RTX 4080" libdirs=ollama,cuda_v13 driver=13.2 pci_id=REDACTED type=discrete total="16.0 GiB" available="14.5 GiB"
time=2026-04-07T17:19:21.122-07:00 level=INFO source=routes.go:1852 msg="vram-based default context" total_vram="16.0 GiB" default_num_ctx=4096
[GIN] 2026/04/07 - 17:19:21 | 200 | 511.5µs | 127.0.0.1 | GET "/api/version"
[GIN] 2026/04/07 - 17:19:21 | 200 | 1.0255ms | 127.0.0.1 | GET "/api/version"
[GIN] 2026/04/07 - 17:19:21 | 200 | 0s | 127.0.0.1 | GET "/api/version"
[GIN] 2026/04/07 - 17:19:21 | 200 | 1.0274ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2026/04/07 - 17:19:21 | 200 | 115.3674ms | 127.0.0.1 | POST "/api/show"
[GIN] 2026/04/07 - 17:19:21 | 401 | 203.1088ms | 127.0.0.1 | POST "/api/me"
[GIN] 2026/04/07 - 17:19:21 | 401 | 202.0785ms | 127.0.0.1 | POST "/api/me"
[GIN] 2026/04/07 - 17:19:24 | 200 | 510µs | 127.0.0.1 | GET "/api/tags"
[GIN] 2026/04/07 - 17:19:24 | 200 | 113.2493ms | 127.0.0.1 | POST "/api/show"
[GIN] 2026/04/07 - 17:19:24 | 200 | 109.5377ms | 127.0.0.1 | POST "/api/show"
time=2026-04-07T17:19:24.343-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 54510"
time=2026-04-07T17:19:24.516-07:00 level=INFO source=cpu_windows.go:148 msg=packages count=1
time=2026-04-07T17:19:24.516-07:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1
time=2026-04-07T17:19:24.516-07:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=24 efficiency=16 threads=32
time=2026-04-07T17:19:24.586-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --model E:\PATH\TO\MODELS\blobs\sha256-81fb60c7daa80fc1123380b98970b320ae233409f0f71a72ed7b9b0d62f40490 --port 54520"
time=2026-04-07T17:19:24.589-07:00 level=INFO source=sched.go:484 msg="system memory" total="63.7 GiB" free="54.3 GiB" free_swap="48.8 GiB"
time=2026-04-07T17:19:24.589-07:00 level=INFO source=sched.go:491 msg="gpu memory" id=GPU-REDACTED library=CUDA available="14.0 GiB" free="14.5 GiB" minimum="457.0 MiB" overhead="0 B"
time=2026-04-07T17:19:24.589-07:00 level=INFO source=server.go:759 msg="loading model" "model layers"=33 requested=-1
time=2026-04-07T17:19:24.676-07:00 level=INFO source=runner.go:1417 msg="starting ollama engine"
time=2026-04-07T17:19:24.677-07:00 level=INFO source=runner.go:1452 msg="Server listening on 127.0.0.1:54520"
time=2026-04-07T17:19:24.685-07:00 level=INFO source=runner.go:1290 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Disabled KvSize:4096 KvCacheType: NumThreads:8 GPULayers:33[ID:GPU-REDACTED Layers:33(0..32)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-04-07T17:19:24.713-07:00 level=INFO source=ggml.go:136 msg="" architecture=qwen35 file_type=Q4_K_M name="" description="" num_tensors=834 num_key_values=52
load_backend: loaded CPU backend from C:\Users\USER\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
Device 0: NVIDIA GeForce RTX 4080, compute capability 8.9, VMM: yes, ID: GPU-REDACTED
load_backend: loaded CUDA backend from C:\Users\USER\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13\ggml-cuda.dll
time=2026-04-07T17:19:24.774-07:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=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 CUDA.0.ARCHS=750,800,860,870,890,900,1000,1030,1100,1200,1210 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
time=2026-04-07T17:19:25.395-07:00 level=INFO source=runner.go:1290 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Disabled KvSize:4096 KvCacheType: NumThreads:8 GPULayers:33[ID:GPU-REDACTED Layers:33(0..32)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-04-07T17:19:25.851-07:00 level=INFO source=runner.go:1290 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Disabled KvSize:4096 KvCacheType: NumThreads:8 GPULayers:33[ID:GPU-REDACTED Layers:33(0..32)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-04-07T17:19:25.851-07:00 level=INFO source=ggml.go:482 msg="offloading 32 repeating layers to GPU"
time=2026-04-07T17:19:25.851-07:00 level=INFO source=ggml.go:489 msg="offloading output layer to GPU"
time=2026-04-07T17:19:25.851-07:00 level=INFO source=ggml.go:494 msg="offloaded 33/33 layers to GPU"
time=2026-04-07T17:19:25.851-07:00 level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="3.1 GiB"
time=2026-04-07T17:19:25.851-07:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="504.4 MiB"
time=2026-04-07T17:19:25.851-07:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="1.4 GiB"
time=2026-04-07T17:19:25.851-07:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="4.3 GiB"
time=2026-04-07T17:19:25.851-07:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="19.8 MiB"
time=2026-04-07T17:19:25.851-07:00 level=INFO source=device.go:272 msg="total memory" size="9.3 GiB"
time=2026-04-07T17:19:25.851-07:00 level=INFO source=sched.go:561 msg="loaded runners" count=1
time=2026-04-07T17:19:25.851-07:00 level=INFO source=server.go:1352 msg="waiting for llama runner to start responding"
time=2026-04-07T17:19:25.851-07:00 level=INFO source=server.go:1386 msg="waiting for server to become available" status="llm server loading model"
time=2026-04-07T17:19:26.852-07:00 level=INFO source=server.go:1390 msg="llama runner started in 2.26 seconds"
panic: failed to sample token

goroutine 1107 [running]:
github.com/ollama/ollama/runner/ollamarunner.(*Server).computeBatch(0xc000218b40, {0x0, {0x7ff7a33822e0, 0xc00061e140}, {0x7ff7a3392498, 0xc0093e5938}, {0xc0002a3780, 0xb, 0x10}, {{0x7ff7a3392498, ...}, ...}, ...})
github.com/ollama/ollama/runner/ollamarunner/runner.go:762 +0x1c25
created by github.com/ollama/ollama/runner/ollamarunner.(*Server).run in goroutine 6
github.com/ollama/ollama/runner/ollamarunner/runner.go:459 +0x2cd
time=2026-04-07T17:19:27.069-07:00 level=ERROR source=server.go:1612 msg="post predict" error="Post "http://127.0.0.1:54520/completion": read tcp 127.0.0.1:54530->127.0.0.1:54520: wsarecv: An existing connection was forcibly closed by the remote host."
[GIN] 2026/04/07 - 17:19:27 | 500 | 2.8181144s | 127.0.0.1 | POST "/api/chat"
[GIN] 2026/04/07 - 17:19:54 | 200 | 1.0193ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2026/04/07 - 17:20:24 | 200 | 802.9µs | 127.0.0.1 | GET "/api/tags"
[GIN] 2026/04/07 - 17:20:54 | 200 | 799.3µs | 127.0.0.1 | GET "/api/tags"
[GIN] 2026/04/07 - 17:21:15 | 200 | 73.4226ms | 127.0.0.1 | POST "/api/show"
[GIN] 2026/04/07 - 17:21:24 | 200 | 1.2399ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2026/04/07 - 17:21:27 | 200 | 66.2095ms | 127.0.0.1 | POST "/api/show"
[GIN] 2026/04/07 - 17:21:27 | 200 | 63.3633ms | 127.0.0.1 | POST "/api/show"
time=2026-04-07T17:21:27.468-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 60219"
time=2026-04-07T17:21:27.669-07:00 level=INFO source=cpu_windows.go:148 msg=packages count=1
time=2026-04-07T17:21:27.669-07:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1
time=2026-04-07T17:21:27.669-07:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=24 efficiency=16 threads=32
time=2026-04-07T17:21:27.669-07:00 level=INFO source=sched.go:627 msg="updated VRAM based on existing loaded models" gpu=GPU-REDACTED library=CUDA total="16.0 GiB" available="7.2 GiB"
time=2026-04-07T17:21:27.712-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --model E:\PATH\TO\MODELS\blobs\sha256-9c60bdd691c1897bbfe5ddbc67336848e18c346b7ee2ab8541b135f208e5bb38 --port 60231"
time=2026-04-07T17:21:27.714-07:00 level=INFO source=sched.go:484 msg="system memory" total="63.7 GiB" free="52.2 GiB" free_swap="46.3 GiB"
time=2026-04-07T17:21:27.714-07:00 level=INFO source=sched.go:491 msg="gpu memory" id=GPU-REDACTED library=CUDA available="6.7 GiB" free="7.2 GiB" minimum="457.0 MiB" overhead="0 B"
time=2026-04-07T17:21:27.714-07:00 level=INFO source=server.go:759 msg="loading model" "model layers"=37 requested=-1
time=2026-04-07T17:21:27.809-07:00 level=INFO source=runner.go:1417 msg="starting ollama engine"
time=2026-04-07T17:21:27.810-07:00 level=INFO source=runner.go:1452 msg="Server listening on 127.0.0.1:60231"
time=2026-04-07T17:21:27.811-07:00 level=INFO source=runner.go:1290 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Disabled KvSize:4096 KvCacheType: NumThreads:8 GPULayers:37[ID:GPU-REDACTED Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-04-07T17:21:27.828-07:00 level=INFO source=ggml.go:136 msg="" architecture=qwen3vl file_type=Q4_K_M name="" description="" num_tensors=809 num_key_values=40
load_backend: loaded CPU backend from C:\Users\USER\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
Device 0: NVIDIA GeForce RTX 4080, compute capability 8.9, VMM: yes, ID: GPU-REDACTED
load_backend: loaded CUDA backend from C:\Users\USER\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13\ggml-cuda.dll
time=2026-04-07T17:21:27.877-07:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=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 CUDA.0.ARCHS=750,800,860,870,890,900,1000,1030,1100,1200,1210 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
time=2026-04-07T17:21:28.246-07:00 level=INFO source=server.go:1031 msg="model requires more gpu memory than is currently available, evicting a model to make space" "loaded layers"=28
time=2026-04-07T17:21:28.246-07:00 level=INFO source=runner.go:1290 msg=load request="{Operation:close LoraPath:[] Parallel:0 BatchSize:0 FlashAttention:Disabled KvSize:0 KvCacheType: NumThreads:0 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-04-07T17:21:28.246-07:00 level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="3.1 GiB"
time=2026-04-07T17:21:28.246-07:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="304.3 MiB"
time=2026-04-07T17:21:28.246-07:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="576.0 MiB"
time=2026-04-07T17:21:28.246-07:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="4.7 GiB"
time=2026-04-07T17:21:28.246-07:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="39.6 MiB"
time=2026-04-07T17:21:28.246-07:00 level=INFO source=device.go:272 msg="total memory" size="8.6 GiB"
time=2026-04-07T17:21:28.257-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 60243"
time=2026-04-07T17:21:28.681-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 60254"
time=2026-04-07T17:21:28.934-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 60265"
time=2026-04-07T17:21:29.101-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 60276"
time=2026-04-07T17:21:29.272-07:00 level=INFO source=cpu_windows.go:148 msg=packages count=1
time=2026-04-07T17:21:29.272-07:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1
time=2026-04-07T17:21:29.272-07:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=24 efficiency=16 threads=32
time=2026-04-07T17:21:29.288-07:00 level=INFO source=sched.go:484 msg="system memory" total="63.7 GiB" free="51.5 GiB" free_swap="41.3 GiB"
time=2026-04-07T17:21:29.288-07:00 level=INFO source=sched.go:491 msg="gpu memory" id=GPU-REDACTED library=CUDA available="13.4 GiB" free="13.8 GiB" minimum="457.0 MiB" overhead="0 B"
time=2026-04-07T17:21:29.288-07:00 level=INFO source=server.go:759 msg="loading model" "model layers"=37 requested=-1
time=2026-04-07T17:21:29.289-07:00 level=INFO source=runner.go:1290 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Disabled KvSize:4096 KvCacheType: NumThreads:8 GPULayers:37[ID:GPU-REDACTED Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-04-07T17:21:29.500-07:00 level=INFO source=runner.go:1290 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Disabled KvSize:4096 KvCacheType: NumThreads:8 GPULayers:37[ID:GPU-REDACTED Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-04-07T17:21:29.820-07:00 level=INFO source=runner.go:1290 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Disabled KvSize:4096 KvCacheType: NumThreads:8 GPULayers:37[ID:GPU-REDACTED Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-04-07T17:21:29.820-07:00 level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="3.1 GiB"
time=2026-04-07T17:21:29.820-07:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="304.3 MiB"
time=2026-04-07T17:21:29.820-07:00 level=INFO source=ggml.go:482 msg="offloading 36 repeating layers to GPU"
time=2026-04-07T17:21:29.820-07:00 level=INFO source=ggml.go:489 msg="offloading output layer to GPU"
time=2026-04-07T17:21:29.820-07:00 level=INFO source=ggml.go:494 msg="offloaded 37/37 layers to GPU"
time=2026-04-07T17:21:29.820-07:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="576.0 MiB"
time=2026-04-07T17:21:29.820-07:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="4.7 GiB"
time=2026-04-07T17:21:29.820-07:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="39.6 MiB"
time=2026-04-07T17:21:29.820-07:00 level=INFO source=device.go:272 msg="total memory" size="8.6 GiB"
time=2026-04-07T17:21:29.820-07:00 level=INFO source=sched.go:561 msg="loaded runners" count=1
time=2026-04-07T17:21:29.820-07:00 level=INFO source=server.go:1352 msg="waiting for llama runner to start responding"
time=2026-04-07T17:21:29.820-07:00 level=INFO source=server.go:1386 msg="waiting for server to become available" status="llm server loading model"
time=2026-04-07T17:21:30.572-07:00 level=INFO source=server.go:1390 msg="llama runner started in 2.86 seconds"
panic: failed to sample token

goroutine 700 [running]:
github.com/ollama/ollama/runner/ollamarunner.(*Server).computeBatch(0xc00022f2c0, {0x0, {0x7ff7a33822e0, 0xc003f62100}, {0x7ff7a3392498, 0xc000ff0468}, {0xc00004ea00, 0x11, 0x20}, {{0x7ff7a3392498, ...}, ...}, ...})
github.com/ollama/ollama/runner/ollamarunner/runner.go:762 +0x1c25
created by github.com/ollama/ollama/runner/ollamarunner.(*Server).run in goroutine 15
github.com/ollama/ollama/runner/ollamarunner/runner.go:459 +0x2cd
time=2026-04-07T17:21:30.746-07:00 level=ERROR source=server.go:1612 msg="post predict" error="Post "http://127.0.0.1:60231/completion": read tcp 127.0.0.1:60241->127.0.0.1:60231: wsarecv: An existing connection was forcibly closed by the remote host."
[GIN] 2026/04/07 - 17:21:30 | 500 | 3.3444095s | 127.0.0.1 | POST "/api/chat"
[GIN] 2026/04/07 - 17:21:54 | 200 | 3.0137ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2026/04/07 - 17:22:24 | 200 | 502.9µs | 127.0.0.1 | GET "/api/tags"
[GIN] 2026/04/07 - 17:22:54 | 200 | 2.8243ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2026/04/07 - 17:23:24 | 200 | 502.4µs | 127.0.0.1 | GET "/api/tags"
[GIN] 2026/04/07 - 17:23:54 | 200 | 1.9837ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2026/04/07 - 17:24:24 | 200 | 1.1573ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2026/04/07 - 17:24:54 | 200 | 548.7µs | 127.0.0.1 | GET "/api/tags"
[GIN] 2026/04/07 - 17:25:24 | 200 | 3.3265ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2026/04/07 - 17:25:54 | 200 | 1.1009ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2026/04/07 - 17:26:24 | 200 | 1.5456ms | 127.0.0.1 | GET "/api/tags"
time=2026-04-07T17:26:30.767-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 55514"
time=2026-04-07T17:26:31.200-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 55526"
time=2026-04-07T17:26:31.448-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 55537"
time=2026-04-07T17:26:31.698-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 55548"
time=2026-04-07T17:26:31.948-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 55559"
time=2026-04-07T17:26:32.199-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 55570"
time=2026-04-07T17:26:32.449-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 55582"
time=2026-04-07T17:26:32.700-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 55593"
time=2026-04-07T17:26:32.948-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 55604"
time=2026-04-07T17:26:33.200-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 55615"
time=2026-04-07T17:26:33.450-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 55627"
time=2026-04-07T17:26:33.698-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 55638"
time=2026-04-07T17:26:33.948-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 55649"
time=2026-04-07T17:26:34.199-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 55660"
time=2026-04-07T17:26:34.449-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 55671"
time=2026-04-07T17:26:34.699-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 55682"
time=2026-04-07T17:26:34.951-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 55693"
time=2026-04-07T17:26:35.199-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 55704"
time=2026-04-07T17:26:35.450-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 55715"
time=2026-04-07T17:26:35.698-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\Users\tctvs\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 55726"
[GIN] 2026/04/07 - 17:26:54 | 200 | 4.5294ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2026/04/07 - 17:27:24 | 200 | 2.6667ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2026/04/07 - 17:27:54 | 200 | 1.0473ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2026/04/07 - 17:28:24 | 200 | 1.0379ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2026/04/07 - 17:28:54 | 200 | 502.7µs | 127.0.0.1 | GET "/api/tags"
[GIN] 2026/04/07 - 17:29:24 | 200 | 2.1349ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2026/04/07 - 17:29:54 | 200 | 2.9422ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2026/04/07 - 17:30:24 | 200 | 504.7µs | 127.0.0.1 | GET "/api/tags"
[GIN] 2026/04/07 - 17:30:54 | 200 | 1.0288ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2026/04/07 - 17:31:24 | 200 | 2.827ms | 127.0.0.1 | GET "/api/tags"

@ch473221 commented on GitHub (Apr 8, 2026): > [Server logs](https://docs.ollama.com/troubleshooting) will aid in debugging. Here is the latest log... time=2026-04-07T17:19:19.939-07:00 level=INFO source=routes.go:1744 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:0 OLLAMA_DEBUG:INFO OLLAMA_DEBUG_LOG_REQUESTS:false OLLAMA_EDITOR: OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 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:E:\\PATH\\TO\\MODELS OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NO_CLOUD: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 OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES:]" time=2026-04-07T17:19:19.939-07:00 level=INFO source=routes.go:1746 msg="Ollama cloud disabled: false" time=2026-04-07T17:19:19.945-07:00 level=INFO source=images.go:499 msg="total blobs: 7" time=2026-04-07T17:19:19.946-07:00 level=INFO source=images.go:506 msg="total unused blobs removed: 0" time=2026-04-07T17:19:19.947-07:00 level=INFO source=routes.go:1802 msg="Listening on 127.0.0.1:11434 (version 0.20.3)" time=2026-04-07T17:19:19.949-07:00 level=INFO source=runner.go:67 msg="discovering available GPUs..." time=2026-04-07T17:19:19.961-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 51530" time=2026-04-07T17:19:20.157-07:00 level=INFO source=runner.go:106 msg="experimental Vulkan support disabled. To enable, set OLLAMA_VULKAN=1" time=2026-04-07T17:19:20.158-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 51542" time=2026-04-07T17:19:20.543-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 51553" time=2026-04-07T17:19:20.891-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 51563" time=2026-04-07T17:19:20.891-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 51564" time=2026-04-07T17:19:21.122-07:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-REDACTED filter_id="" library=CUDA compute=8.9 name=CUDA0 description="NVIDIA GeForce RTX 4080" libdirs=ollama,cuda_v13 driver=13.2 pci_id=REDACTED type=discrete total="16.0 GiB" available="14.5 GiB" time=2026-04-07T17:19:21.122-07:00 level=INFO source=routes.go:1852 msg="vram-based default context" total_vram="16.0 GiB" default_num_ctx=4096 [GIN] 2026/04/07 - 17:19:21 | 200 | 511.5µs | 127.0.0.1 | GET "/api/version" [GIN] 2026/04/07 - 17:19:21 | 200 | 1.0255ms | 127.0.0.1 | GET "/api/version" [GIN] 2026/04/07 - 17:19:21 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2026/04/07 - 17:19:21 | 200 | 1.0274ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/04/07 - 17:19:21 | 200 | 115.3674ms | 127.0.0.1 | POST "/api/show" [GIN] 2026/04/07 - 17:19:21 | 401 | 203.1088ms | 127.0.0.1 | POST "/api/me" [GIN] 2026/04/07 - 17:19:21 | 401 | 202.0785ms | 127.0.0.1 | POST "/api/me" [GIN] 2026/04/07 - 17:19:24 | 200 | 510µs | 127.0.0.1 | GET "/api/tags" [GIN] 2026/04/07 - 17:19:24 | 200 | 113.2493ms | 127.0.0.1 | POST "/api/show" [GIN] 2026/04/07 - 17:19:24 | 200 | 109.5377ms | 127.0.0.1 | POST "/api/show" time=2026-04-07T17:19:24.343-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 54510" time=2026-04-07T17:19:24.516-07:00 level=INFO source=cpu_windows.go:148 msg=packages count=1 time=2026-04-07T17:19:24.516-07:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1 time=2026-04-07T17:19:24.516-07:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=24 efficiency=16 threads=32 time=2026-04-07T17:19:24.586-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model E:\\PATH\\TO\\MODELS\\blobs\\sha256-81fb60c7daa80fc1123380b98970b320ae233409f0f71a72ed7b9b0d62f40490 --port 54520" time=2026-04-07T17:19:24.589-07:00 level=INFO source=sched.go:484 msg="system memory" total="63.7 GiB" free="54.3 GiB" free_swap="48.8 GiB" time=2026-04-07T17:19:24.589-07:00 level=INFO source=sched.go:491 msg="gpu memory" id=GPU-REDACTED library=CUDA available="14.0 GiB" free="14.5 GiB" minimum="457.0 MiB" overhead="0 B" time=2026-04-07T17:19:24.589-07:00 level=INFO source=server.go:759 msg="loading model" "model layers"=33 requested=-1 time=2026-04-07T17:19:24.676-07:00 level=INFO source=runner.go:1417 msg="starting ollama engine" time=2026-04-07T17:19:24.677-07:00 level=INFO source=runner.go:1452 msg="Server listening on 127.0.0.1:54520" time=2026-04-07T17:19:24.685-07:00 level=INFO source=runner.go:1290 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Disabled KvSize:4096 KvCacheType: NumThreads:8 GPULayers:33[ID:GPU-REDACTED Layers:33(0..32)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-04-07T17:19:24.713-07:00 level=INFO source=ggml.go:136 msg="" architecture=qwen35 file_type=Q4_K_M name="" description="" num_tensors=834 num_key_values=52 load_backend: loaded CPU backend from C:\Users\USER\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 4080, compute capability 8.9, VMM: yes, ID: GPU-REDACTED load_backend: loaded CUDA backend from C:\Users\USER\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13\ggml-cuda.dll time=2026-04-07T17:19:24.774-07:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=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 CUDA.0.ARCHS=750,800,860,870,890,900,1000,1030,1100,1200,1210 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang) time=2026-04-07T17:19:25.395-07:00 level=INFO source=runner.go:1290 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Disabled KvSize:4096 KvCacheType: NumThreads:8 GPULayers:33[ID:GPU-REDACTED Layers:33(0..32)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-04-07T17:19:25.851-07:00 level=INFO source=runner.go:1290 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Disabled KvSize:4096 KvCacheType: NumThreads:8 GPULayers:33[ID:GPU-REDACTED Layers:33(0..32)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-04-07T17:19:25.851-07:00 level=INFO source=ggml.go:482 msg="offloading 32 repeating layers to GPU" time=2026-04-07T17:19:25.851-07:00 level=INFO source=ggml.go:489 msg="offloading output layer to GPU" time=2026-04-07T17:19:25.851-07:00 level=INFO source=ggml.go:494 msg="offloaded 33/33 layers to GPU" time=2026-04-07T17:19:25.851-07:00 level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="3.1 GiB" time=2026-04-07T17:19:25.851-07:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="504.4 MiB" time=2026-04-07T17:19:25.851-07:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="1.4 GiB" time=2026-04-07T17:19:25.851-07:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="4.3 GiB" time=2026-04-07T17:19:25.851-07:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="19.8 MiB" time=2026-04-07T17:19:25.851-07:00 level=INFO source=device.go:272 msg="total memory" size="9.3 GiB" time=2026-04-07T17:19:25.851-07:00 level=INFO source=sched.go:561 msg="loaded runners" count=1 time=2026-04-07T17:19:25.851-07:00 level=INFO source=server.go:1352 msg="waiting for llama runner to start responding" time=2026-04-07T17:19:25.851-07:00 level=INFO source=server.go:1386 msg="waiting for server to become available" status="llm server loading model" time=2026-04-07T17:19:26.852-07:00 level=INFO source=server.go:1390 msg="llama runner started in 2.26 seconds" panic: failed to sample token goroutine 1107 [running]: github.com/ollama/ollama/runner/ollamarunner.(*Server).computeBatch(0xc000218b40, {0x0, {0x7ff7a33822e0, 0xc00061e140}, {0x7ff7a3392498, 0xc0093e5938}, {0xc0002a3780, 0xb, 0x10}, {{0x7ff7a3392498, ...}, ...}, ...}) github.com/ollama/ollama/runner/ollamarunner/runner.go:762 +0x1c25 created by github.com/ollama/ollama/runner/ollamarunner.(*Server).run in goroutine 6 github.com/ollama/ollama/runner/ollamarunner/runner.go:459 +0x2cd time=2026-04-07T17:19:27.069-07:00 level=ERROR source=server.go:1612 msg="post predict" error="Post \"http://127.0.0.1:54520/completion\": read tcp 127.0.0.1:54530->127.0.0.1:54520: wsarecv: An existing connection was forcibly closed by the remote host." [GIN] 2026/04/07 - 17:19:27 | 500 | 2.8181144s | 127.0.0.1 | POST "/api/chat" [GIN] 2026/04/07 - 17:19:54 | 200 | 1.0193ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/04/07 - 17:20:24 | 200 | 802.9µs | 127.0.0.1 | GET "/api/tags" [GIN] 2026/04/07 - 17:20:54 | 200 | 799.3µs | 127.0.0.1 | GET "/api/tags" [GIN] 2026/04/07 - 17:21:15 | 200 | 73.4226ms | 127.0.0.1 | POST "/api/show" [GIN] 2026/04/07 - 17:21:24 | 200 | 1.2399ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/04/07 - 17:21:27 | 200 | 66.2095ms | 127.0.0.1 | POST "/api/show" [GIN] 2026/04/07 - 17:21:27 | 200 | 63.3633ms | 127.0.0.1 | POST "/api/show" time=2026-04-07T17:21:27.468-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60219" time=2026-04-07T17:21:27.669-07:00 level=INFO source=cpu_windows.go:148 msg=packages count=1 time=2026-04-07T17:21:27.669-07:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1 time=2026-04-07T17:21:27.669-07:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=24 efficiency=16 threads=32 time=2026-04-07T17:21:27.669-07:00 level=INFO source=sched.go:627 msg="updated VRAM based on existing loaded models" gpu=GPU-REDACTED library=CUDA total="16.0 GiB" available="7.2 GiB" time=2026-04-07T17:21:27.712-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model E:\\PATH\\TO\\MODELS\\blobs\\sha256-9c60bdd691c1897bbfe5ddbc67336848e18c346b7ee2ab8541b135f208e5bb38 --port 60231" time=2026-04-07T17:21:27.714-07:00 level=INFO source=sched.go:484 msg="system memory" total="63.7 GiB" free="52.2 GiB" free_swap="46.3 GiB" time=2026-04-07T17:21:27.714-07:00 level=INFO source=sched.go:491 msg="gpu memory" id=GPU-REDACTED library=CUDA available="6.7 GiB" free="7.2 GiB" minimum="457.0 MiB" overhead="0 B" time=2026-04-07T17:21:27.714-07:00 level=INFO source=server.go:759 msg="loading model" "model layers"=37 requested=-1 time=2026-04-07T17:21:27.809-07:00 level=INFO source=runner.go:1417 msg="starting ollama engine" time=2026-04-07T17:21:27.810-07:00 level=INFO source=runner.go:1452 msg="Server listening on 127.0.0.1:60231" time=2026-04-07T17:21:27.811-07:00 level=INFO source=runner.go:1290 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Disabled KvSize:4096 KvCacheType: NumThreads:8 GPULayers:37[ID:GPU-REDACTED Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-04-07T17:21:27.828-07:00 level=INFO source=ggml.go:136 msg="" architecture=qwen3vl file_type=Q4_K_M name="" description="" num_tensors=809 num_key_values=40 load_backend: loaded CPU backend from C:\Users\USER\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 4080, compute capability 8.9, VMM: yes, ID: GPU-REDACTED load_backend: loaded CUDA backend from C:\Users\USER\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13\ggml-cuda.dll time=2026-04-07T17:21:27.877-07:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=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 CUDA.0.ARCHS=750,800,860,870,890,900,1000,1030,1100,1200,1210 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang) time=2026-04-07T17:21:28.246-07:00 level=INFO source=server.go:1031 msg="model requires more gpu memory than is currently available, evicting a model to make space" "loaded layers"=28 time=2026-04-07T17:21:28.246-07:00 level=INFO source=runner.go:1290 msg=load request="{Operation:close LoraPath:[] Parallel:0 BatchSize:0 FlashAttention:Disabled KvSize:0 KvCacheType: NumThreads:0 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-04-07T17:21:28.246-07:00 level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="3.1 GiB" time=2026-04-07T17:21:28.246-07:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="304.3 MiB" time=2026-04-07T17:21:28.246-07:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="576.0 MiB" time=2026-04-07T17:21:28.246-07:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="4.7 GiB" time=2026-04-07T17:21:28.246-07:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="39.6 MiB" time=2026-04-07T17:21:28.246-07:00 level=INFO source=device.go:272 msg="total memory" size="8.6 GiB" time=2026-04-07T17:21:28.257-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60243" time=2026-04-07T17:21:28.681-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60254" time=2026-04-07T17:21:28.934-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60265" time=2026-04-07T17:21:29.101-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60276" time=2026-04-07T17:21:29.272-07:00 level=INFO source=cpu_windows.go:148 msg=packages count=1 time=2026-04-07T17:21:29.272-07:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1 time=2026-04-07T17:21:29.272-07:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=24 efficiency=16 threads=32 time=2026-04-07T17:21:29.288-07:00 level=INFO source=sched.go:484 msg="system memory" total="63.7 GiB" free="51.5 GiB" free_swap="41.3 GiB" time=2026-04-07T17:21:29.288-07:00 level=INFO source=sched.go:491 msg="gpu memory" id=GPU-REDACTED library=CUDA available="13.4 GiB" free="13.8 GiB" minimum="457.0 MiB" overhead="0 B" time=2026-04-07T17:21:29.288-07:00 level=INFO source=server.go:759 msg="loading model" "model layers"=37 requested=-1 time=2026-04-07T17:21:29.289-07:00 level=INFO source=runner.go:1290 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Disabled KvSize:4096 KvCacheType: NumThreads:8 GPULayers:37[ID:GPU-REDACTED Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-04-07T17:21:29.500-07:00 level=INFO source=runner.go:1290 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Disabled KvSize:4096 KvCacheType: NumThreads:8 GPULayers:37[ID:GPU-REDACTED Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-04-07T17:21:29.820-07:00 level=INFO source=runner.go:1290 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Disabled KvSize:4096 KvCacheType: NumThreads:8 GPULayers:37[ID:GPU-REDACTED Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-04-07T17:21:29.820-07:00 level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="3.1 GiB" time=2026-04-07T17:21:29.820-07:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="304.3 MiB" time=2026-04-07T17:21:29.820-07:00 level=INFO source=ggml.go:482 msg="offloading 36 repeating layers to GPU" time=2026-04-07T17:21:29.820-07:00 level=INFO source=ggml.go:489 msg="offloading output layer to GPU" time=2026-04-07T17:21:29.820-07:00 level=INFO source=ggml.go:494 msg="offloaded 37/37 layers to GPU" time=2026-04-07T17:21:29.820-07:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="576.0 MiB" time=2026-04-07T17:21:29.820-07:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="4.7 GiB" time=2026-04-07T17:21:29.820-07:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="39.6 MiB" time=2026-04-07T17:21:29.820-07:00 level=INFO source=device.go:272 msg="total memory" size="8.6 GiB" time=2026-04-07T17:21:29.820-07:00 level=INFO source=sched.go:561 msg="loaded runners" count=1 time=2026-04-07T17:21:29.820-07:00 level=INFO source=server.go:1352 msg="waiting for llama runner to start responding" time=2026-04-07T17:21:29.820-07:00 level=INFO source=server.go:1386 msg="waiting for server to become available" status="llm server loading model" time=2026-04-07T17:21:30.572-07:00 level=INFO source=server.go:1390 msg="llama runner started in 2.86 seconds" panic: failed to sample token goroutine 700 [running]: github.com/ollama/ollama/runner/ollamarunner.(*Server).computeBatch(0xc00022f2c0, {0x0, {0x7ff7a33822e0, 0xc003f62100}, {0x7ff7a3392498, 0xc000ff0468}, {0xc00004ea00, 0x11, 0x20}, {{0x7ff7a3392498, ...}, ...}, ...}) github.com/ollama/ollama/runner/ollamarunner/runner.go:762 +0x1c25 created by github.com/ollama/ollama/runner/ollamarunner.(*Server).run in goroutine 15 github.com/ollama/ollama/runner/ollamarunner/runner.go:459 +0x2cd time=2026-04-07T17:21:30.746-07:00 level=ERROR source=server.go:1612 msg="post predict" error="Post \"http://127.0.0.1:60231/completion\": read tcp 127.0.0.1:60241->127.0.0.1:60231: wsarecv: An existing connection was forcibly closed by the remote host." [GIN] 2026/04/07 - 17:21:30 | 500 | 3.3444095s | 127.0.0.1 | POST "/api/chat" [GIN] 2026/04/07 - 17:21:54 | 200 | 3.0137ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/04/07 - 17:22:24 | 200 | 502.9µs | 127.0.0.1 | GET "/api/tags" [GIN] 2026/04/07 - 17:22:54 | 200 | 2.8243ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/04/07 - 17:23:24 | 200 | 502.4µs | 127.0.0.1 | GET "/api/tags" [GIN] 2026/04/07 - 17:23:54 | 200 | 1.9837ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/04/07 - 17:24:24 | 200 | 1.1573ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/04/07 - 17:24:54 | 200 | 548.7µs | 127.0.0.1 | GET "/api/tags" [GIN] 2026/04/07 - 17:25:24 | 200 | 3.3265ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/04/07 - 17:25:54 | 200 | 1.1009ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/04/07 - 17:26:24 | 200 | 1.5456ms | 127.0.0.1 | GET "/api/tags" time=2026-04-07T17:26:30.767-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 55514" time=2026-04-07T17:26:31.200-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 55526" time=2026-04-07T17:26:31.448-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 55537" time=2026-04-07T17:26:31.698-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 55548" time=2026-04-07T17:26:31.948-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 55559" time=2026-04-07T17:26:32.199-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 55570" time=2026-04-07T17:26:32.449-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 55582" time=2026-04-07T17:26:32.700-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 55593" time=2026-04-07T17:26:32.948-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 55604" time=2026-04-07T17:26:33.200-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 55615" time=2026-04-07T17:26:33.450-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 55627" time=2026-04-07T17:26:33.698-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 55638" time=2026-04-07T17:26:33.948-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 55649" time=2026-04-07T17:26:34.199-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 55660" time=2026-04-07T17:26:34.449-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 55671" time=2026-04-07T17:26:34.699-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 55682" time=2026-04-07T17:26:34.951-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 55693" time=2026-04-07T17:26:35.199-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 55704" time=2026-04-07T17:26:35.450-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 55715" time=2026-04-07T17:26:35.698-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\tctvs\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 55726" [GIN] 2026/04/07 - 17:26:54 | 200 | 4.5294ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/04/07 - 17:27:24 | 200 | 2.6667ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/04/07 - 17:27:54 | 200 | 1.0473ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/04/07 - 17:28:24 | 200 | 1.0379ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/04/07 - 17:28:54 | 200 | 502.7µs | 127.0.0.1 | GET "/api/tags" [GIN] 2026/04/07 - 17:29:24 | 200 | 2.1349ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/04/07 - 17:29:54 | 200 | 2.9422ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/04/07 - 17:30:24 | 200 | 504.7µs | 127.0.0.1 | GET "/api/tags" [GIN] 2026/04/07 - 17:30:54 | 200 | 1.0288ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/04/07 - 17:31:24 | 200 | 2.827ms | 127.0.0.1 | GET "/api/tags"

GiteaMirror commented

2026-05-05 02:56:19 -05:00

@ch473221 commented on GitHub (Apr 9, 2026):

OK, found the issue, theres a workaround, but its a bit annoying. This seems to be a combo drive-specific/Ollama write issue as I pulled a model on a different drive that survives a reboot. I've isolated this as a manifest write issue. I pulled a model, ran fine, rebooted, got the 500 error. Tried rebooting again and this time pulled the same model that gave the 500 error. Since the models blobs were already saved, it rewrote the manifest and boom, the model worked in that session and has survived reboots. So there's a bug in the initial manifest write. For reference the models are on a 4t gen 5 nvme. Hope this helps someone.

@ch473221 commented on GitHub (Apr 9, 2026): OK, found the issue, theres a workaround, but its a bit annoying. This seems to be a combo drive-specific/Ollama write issue as I pulled a model on a different drive that survives a reboot. I've isolated this as a manifest write issue. I pulled a model, ran fine, rebooted, got the 500 error. Tried rebooting again and this time pulled the same model that gave the 500 error. Since the models blobs were already saved, it rewrote the manifest and boom, the model worked in that session and has survived reboots. So there's a bug in the initial manifest write. For reference the models are on a 4t gen 5 nvme. Hope this helps someone.

GiteaMirror commented

2026-05-05 02:56:20 -05:00

@PureBlissAK commented on GitHub (Apr 18, 2026):

🤖 Automated Triage & Analysis Report

Issue: #15410
Analyzed: 2026-04-18T18:22:20.337179

Analysis

Type: unknown
Severity: medium
Components: unknown

Implementation Plan

Effort: medium
Steps:

This issue has been triaged and marked for implementation.

@PureBlissAK commented on GitHub (Apr 18, 2026):  ## 🤖 Automated Triage & Analysis Report **Issue**: #15410 **Analyzed**: 2026-04-18T18:22:20.337179 ### Analysis - **Type**: unknown - **Severity**: medium - **Components**: unknown ### Implementation Plan - **Effort**: medium - **Steps**: *This issue has been triaged and marked for implementation.*

Sign in to join this conversation.

Branches Tags

main

dhiltgen/ci

dhiltgen/llama-runner

hoyyeva/anthropic-local-image-path

hoyyeva/anthropic-reference-images-path

parth-anthropic-reference-images-path

brucemacd/download-before-remove

hoyyeva/editor-config-repair

parth-mlx-decode-checkpoints

parth-launch-codex-app

hoyyeva/fix-codex-model-metadata-warning

hoyyeva/qwen

parth/hide-claude-desktop-till-release

hoyyeva/opencode-image-modality

parth-add-claude-code-autoinstall

release_v0.22.0

pdevine/manifest-list

codex/fix-codex-model-metadata-warning

pdevine/addressable-manifest

brucemacd/launch-fetch-reccomended

jmorganca/llama-compat

launch-copilot-cli

hoyyeva/opencode-thinking

release_v0.20.7

parth-auto-save-backup

parth-test

jmorganca/gemma4-audio-replacements

fix-manifest-digest-on-pull

hoyyeva/vscode-improve

brucemacd/install-server-wait

parth/update-claude-docs

brucemac/start-ap-install

pdevine/mlx-update

pdevine/qwen35_vision

drifkin/api-show-fallback

mintlify/image-generation-1773352582

hoyyeva/server-context-length-local-config

jmorganca/faster-reptition-penalties

jmorganca/convert-nemotron

parth-pi-thinking

pdevine/sampling-penalties

jmorganca/fix-create-quantization-memory

dongchen/resumable_transfer_fix

pdevine/sampling-cache-error

jessegross/mlx-usage

hoyyeva/openclaw-config

hoyyeva/app-html

pdevine/qwen3next

brucemacd/sign-sh-install

brucemacd/tui-update

brucemacd/usage-api

jmorganca/launch-empty

fix-app-dist-embed

mxyng/mlx-compile

mxyng/mlx-quant

mxyng/mlx-glm4.7

mxyng/mlx

brucemacd/simplify-model-picker

jmorganca/qwen3-concurrent

fix-glm-4.7-flash-mla-config

drifkin/qwen3-coder-opening-tag

brucemacd/usage-cli

fix-cuda12-fattn-shmem

ollama-imagegen-docs

parth/fix-multiline-inputs

brucemacd/config-docs

mxyng/model-files

mxyng/simple-execute

fix-imagegen-ollama-models

mxyng/async-upload

jmorganca/lazy-no-dtype-changes

imagegen-auto-detect-create

parth/decrease-concurrent-download-hf

fix-mlx-quantize-init

jmorganca/x-cleanup

usage

imagegen-readme

jmorganca/glm-image

mlx-gpu-cd

jmorganca/imagegen-modelfile

parth/agent-skills

parth/agent-allowlist

parth/signed-in-offline

parth/agents

parth/fix-context-chopping

improve-cloud-flow

parth/add-models-websearch

parth/prompt-renderer-mcp

jmorganca/native-settings

jmorganca/download-stream-hash

jmorganca/client2-rebased

brucemacd/oai-chat-req-multipart

jessegross/multi_chunk_reserve

grace/additional-omit-empty

grace/mistral-3-large

mxyng/tokenizer2

mxyng/tokenizer

jessegross/flash

hoyyeva/windows-nacked-app

mxyng/cleanup-attention

grace/deepseek-parser

hoyyeva/remember-unsent-prompt

parth/add-lfs-pointer-error-conversion

parth/olmo2-test2

hoyyeva/ollama-launchagent-plist

nicole/olmo-model

parth/olmo-test

mxyng/remove-embedded

parth/render-template

jmorganca/intellect-3

parth/remove-prealloc-linter

jmorganca/cmd-eval

nicole/nomic-embed-text-fix

mxyng/lint-2

hoyyeva/add-gemini-3-pro-preview

hoyyeva/load-model-list

mxyng/expand-path

mxyng/environ-2

hoyyeva/deeplink-json-encoding

parth/improve-tool-calling-tests

hoyyeva/conversation

hoyyeva/assistant-edit-response

hoyyeva/thinking

origin/brucemacd/invalid-char-i-err

parth/improve-tool-calling

jmorganca/required-omitempty

grace/qwen3-vl-tests

mxyng/iter-client

parth/docs-readme

nicole/embed-test

pdevine/integration-benchstat

parth/remove-generate-cmd

parth/add-toolcall-id

mxyng/server-tests

jmorganca/glm-4.6

jmorganca/gin-h-compat

drifkin/stable-tool-args

pdevine/qwen3-more-thinking

parth/add-websearch-client

nicole/websearch_local

jmorganca/qwen3-coder-updates

grace/deepseek-v3-migration-tests

mxyng/fix-create

jmorganca/cloud-errors

pdevine/parser-tidy

revert-12233-parth/simplify-entrypoints-runner

parth/enable-so-gpt-oss

brucemacd/qwen3vl

jmorganca/readme-simplify

parth/gpt-oss-structured-outputs

revert-12039-jmorganca/tools-braces

mxyng/embeddings

mxyng/gguf

mxyng/benchmark

mxyng/types-null

parth/move-parsing

mxyng/gemma2

jmorganca/docs

mxyng/16-bit

mxyng/create-stdin

pdevine/authorizedkeys

mxyng/quant

parth/opt-in-error-context-window

brucemacd/cache-models

brucemacd/runner-completion

jmorganca/llama-update-6

brucemacd/benchmark-list

brucemacd/partial-read-caps

parth/deepseek-r1-tools

mxyng/omit-array

parth/tool-prefix-temp

brucemacd/runner-test

jmorganca/qwen25vl

brucemacd/model-forward-test-ext

parth/python-function-parsing

jmorganca/cuda-compression-none

drifkin/num-parallel

drifkin/chat-truncation-fix

jmorganca/sync

parth/python-tools-calling

drifkin/array-head-count

brucemacd/create-no-loop

parth/server-enable-content-stream-with-tools

qwen25omni

mxyng/v3

brucemacd/ropeconfig

jmorganca/silence-tokenizer

parth/sample-so-test

parth/sampling-structured-outputs

brucemacd/doc-go-engine

parth/constrained-sampling-json

jmorganca/mistral-wip

brucemacd/mistral-small-convert

parth/sample-unmarshal-json-for-params

brucemacd/jomorganca/mistral

pdevine/bfloat16

jmorganca/mistral

brucemacd/mistral

pdevine/logging

parth/sample-correctness-fix

parth/sample-fix-sorting

jmorgan/sample-fix-sorting-extras

jmorganca/temp-0-images

brucemacd/parallel-embed-models

brucemacd/shim-grammar

jmorganca/fix-gguf-error

bmizerany/nameswork

jmorganca/faster-releases

bmizerany/validatenames

brucemacd/err-no-vocab

brucemacd/rope-config

brucemacd/err-hint

brucemacd/qwen2_5

brucemacd/logprobs

brucemacd/new_runner_graph_bench

progress-flicker

brucemacd/forward-test

brucemacd/go_qwen2

pdevine/gemma2

jmorganca/add-missing-symlink-eval

mxyng/next-debug

parth/set-context-size-openai

brucemacd/next-bpe-bench

brucemacd/next-bpe-test

brucemacd/new_runner_e2e

brucemacd/new_runner_qwen2

pdevine/convert-cohere2

brucemacd/convert-cli

parth/log-probs

mxyng/next-mlx

mxyng/cmd-history

parth/templating

parth/tokenize-detokenize

brucemacd/check-key-register

bmizerany/grammar

jmorganca/vendor-081b29bd

mxyng/func-checks

jmorganca/fix-null-format

parth/fix-default-to-warn-json

jmorganca/qwen2vl

jmorganca/no-concat

parth/cmd-cleanup-SO

brucemacd/check-key-register-structured-err

parth/openai-stream-usage

parth/fix-referencing-so

stream-tools-stop

jmorganca/degin-1

brucemacd/install-path-clean

brucemacd/push-name-validation

brucemacd/browser-key-register

jmorganca/openai-fix-first-message

jmorganca/fix-proxy

jessegross/sample

parth/disallow-streaming-tools

dhiltgen/remove_submodule

jmorganca/ga

jmorganca/mllama

pdevine/newlines

pdevine/geems-2b

jmorganca/llama-bump

mxyng/modelname-7

mxyng/gin-slog

mxyng/modelname-6

jyan/convert-prog

jyan/quant5

paligemma-support

pdevine/import-docs

jmorganca/openai-context

jyan/paligemma

jyan/p2

jyan/palitest

bmizerany/embedspeedup

jmorganca/llama-vit

brucemacd/allow-ollama

royh/ep-methods

royh/whisper

mxyng/api-models

mxyng/fix-memory

jyan/q4_4/8

jyan/ollama-v

royh/stream-tools

roy-embed-parallel

bmizerany/hrm

revert-5963-revert-5924-mxyng/llama3.1-rope

royh/embed-viz

jyan/local2

jyan/auth

jyan/local

jyan/parse-temp

jmorganca/template-mistral

jyan/reord-g

royh-openai-suffixdocs

royh-imgembed

royh-embed-parallel

jyan/quant4

royh-precision

jyan/progress

pdevine/fix-template

jyan/quant3

pdevine/ggla

mxyng/update-registry-domain

jmorganca/ggml-static

mxyng/create-context

jyan/v0.146

mxyng/layers-from-files

build_dist

bmizerany/noseek

royh-ls

royh-name

timeout

mxyng/server-timestamp

bmizerany/nosillyggufslurps

royh-params

jmorganca/llama-cpp-7c26775

royh-openai-delete

royh-show-rigid

jmorganca/enable-fa

jmorganca/no-error-template

jyan/format

royh-testdelete

bmizerany/fastverify

language_support

pdevine/ps-glitches

brucemacd/tokenize

bruce/iq-quants

bmizerany/filepathwithcoloninhost

mxyng/split-bin

bmizerany/client-registry

jmorganca/if-none-match

native

jmorganca/native

jmorganca/batch-embeddings

jmorganca/initcmake

jmorganca/mm

pdevine/showggmlinfo

modenameenforcealphanum

bmizerany/modenameenforcealphanum

jmorganca/done-reason

jmorganca/llama-cpp-8960fe8

ollama.com

bmizerany/filepathnobuild

bmizerany/types/model/defaultfix

rmdisplaylong

nogogen

bmizerany/x

modelfile-readme

bmizerany/replacecolon

jmorganca/limit

jmorganca/execstack

jmorganca/replace-assets

mxyng/tune-concurrency

jmorganca/testing

whitespace-detection

jmorganca/options

upgrade-all

scratch

cuda-search

mattw/airenamer

mattw/allmodelsonhuggingface

mattw/quantcontext

mattw/whatneedstorun

brucemacd/llama-mem-calc

mattw/faq-context

mattw/communitylinks

mattw/noprune

mattw/python-functioncalling

rename

mxyng/install

pulse

remove-first

editor

mattw/selfqueryingretrieval

cgo

mattw/howtoquant

api

matt/streamingapi

format-config

mxyng/extra-args

shell

update-nous-hermes

cp-model

upload-progress

fix-unknown-model

fix-model-names

delete-fix

insecure-registry

ls

deletemodels

progressbar

readme-updates

license-layers

skip-list

list-models

modelpath

matt/examplemodelfiles

distribution

go-opts

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/ollama#71913