[GH-ISSUE #14117] glm-ocr: failed to fully read image, stopped with "done": false #55723

New Issue

Open

opened 2026-04-29 09:38:37 -05:00 by GiteaMirror · 5 comments

GiteaMirror commented 2026-04-29 09:38:37 -05:00

Owner

Copy Link

Originally created by @illusdolphin on GitHub (Feb 6, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14117

What is the issue?

Ollama stops on this image, while others works fine. Expected to have more text (see image to see that this is only 1 item from many on image).
Expected: text is extracted after "......".
Actually: it stops.

Ollama: latest 0.15.5
Windows (latest)
GPU: RTX 6000 pro max-Q 96GB VRAM

Request resulted in (via API or CLI result is the same):

{
    "model": "glm-ocr:latest",
    "created_at": "2026-02-06T10:01:23.4538287Z",
    "message": {
        "role": "assistant",
        "content": "IV. Podane w nawiasie przymiotniki proszę przekształcić na stopień najwyższy.\nPrzyklad: Ta ulica jest (szeroka) najszersza w naszym mieście.\n1. To jest (elegancki) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ."
    },
    "done": false
}

POST /api/chat

{
    "model": "glm-ocr:latest",
    "stream": false,
    "options": {
        "num_ctx": 8196
    },
    "messages": [
        {
            "role": "user",
            "content": "OCR <image>",
            "images": ["base64"]
        }
    ]
}

Image 1180x721 below (not too big, but attached as file to avoid huge base64 text):

The same result when using CLI:
ollama run glm-ocr Text Recognition: ./image.png

From logs I see that ollama reaches some limit, but it looks like an issue:
time=2026-02-06T11:04:04.085+01:00 level=DEBUG source=server.go:1661 msg="prediction aborted, token repeat limit reached"

What did I try:

• Reduce OLLAMA_NUM_PARALLEL to 1
• Remove OLLAMA_FLASH_ATTENTION, OLLAMA_NEW_ENGINE, OLLAMA_NEW_ESTIMATES
• Increase context length (up to ~40k, at ~80k ollama fails to process request)
• Change image proportions
• Change prompt

Relevant log output

time=2026-02-06T11:03:12.238+01:00 level=INFO source=routes.go:1636 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 OLLAMA_FLASH_ATTENTION:true OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 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:C:\\Ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:true OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:2 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=2026-02-06T11:03:12.253+01:00 level=INFO source=images.go:473 msg="total blobs: 173"
time=2026-02-06T11:03:12.258+01:00 level=INFO source=images.go:480 msg="total unused blobs removed: 0"
time=2026-02-06T11:03:12.262+01:00 level=INFO source=routes.go:1689 msg="Listening on [::]:11434 (version 0.15.5)"
time=2026-02-06T11:03:12.263+01:00 level=DEBUG source=sched.go:121 msg="starting llm scheduler"
time=2026-02-06T11:03:12.264+01:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
time=2026-02-06T11:03:12.276+01:00 level=INFO source=server.go:430 msg="starting runner" cmd="C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 52100"
time=2026-02-06T11:03:12.277+01:00 level=DEBUG source=server.go:431 msg=subprocess OLLAMA_MODELS=C:\Ollama\models PATH="C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\java8path;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\javapath;C:\\Program Files\\Microsoft SDKs\\Azure\\CLI2\\wbin;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\Program Files\\NVIDIA Corporation\\NVIDIA app\\NvDLISR;C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common;C:\\Program Files\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\170\\Tools\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\160\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\160\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\160\\DTS\\Binn\\;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Local\\nvm\\Current\\nodejs;C:\\Program Files\\Certbot\\bin;C:\\Program Files\\FirefoxPWA\\;C:\\Program Files\\Microsoft SQL Server\\170\\Tools\\Binn\\;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\Program Files (x86)\\Microsoft SQL Server\\170\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\180\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\170\\DTS\\Binn\\;C:\\Program Files\\Go\\bin;C:\\Program Files\\cursor\\resources\\app\\bin;C:\\Program Files\\Git\\cmd;C:\\Program Files\\dotnet\\;C:\\Users\\user\\AppData\\Local\\Programs\\Python\\Python310\\Scripts\\;C:\\Users\\user\\AppData\\Local\\Programs\\Python\\Python310\\;C:\\Users\\user\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\user\\.dotnet\\tools;C:\\Users\\user\\AppData\\Local\\Programs\\Microsoft VS Code\\bin;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Roaming\\npm;C:\\Users\\user\\.lmstudio\\bin;C:\\Users\\user\\AppData\\Local\\Programs\\Ollama;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Local\\nvm\\Current\\nodejs;C:\\Program Files\\OpenSSL-Win64\\bin\\;G:\\Work\\Tools\\GitClean;C:\\Users\\user\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\user\\AppData\\Local\\Programs\\Antigravity\\bin;C:\\Users\\user\\go\\bin;C:\\Users\\user\\.dotnet\\tools" OLLAMA_NEW_ESTIMATES=1 OLLAMA_FLASH_ATTENTION=1 OLLAMA_HOST=0.0.0.0 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_NEW_ENGINE=1 OLLAMA_DEBUG=1 OLLAMA_NUM_PARALLEL=2 OLLAMA_LIBRARY_PATH=C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12
time=2026-02-06T11:03:15.510+01:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=3.2398578s 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=2026-02-06T11:03:15.511+01:00 level=INFO source=server.go:430 msg="starting runner" cmd="C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62301"
time=2026-02-06T11:03:15.511+01:00 level=DEBUG source=server.go:431 msg=subprocess OLLAMA_MODELS=C:\Ollama\models PATH="C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\java8path;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\javapath;C:\\Program Files\\Microsoft SDKs\\Azure\\CLI2\\wbin;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\Program Files\\NVIDIA Corporation\\NVIDIA app\\NvDLISR;C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common;C:\\Program Files\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\170\\Tools\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\160\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\160\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\160\\DTS\\Binn\\;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Local\\nvm\\Current\\nodejs;C:\\Program Files\\Certbot\\bin;C:\\Program Files\\FirefoxPWA\\;C:\\Program Files\\Microsoft SQL Server\\170\\Tools\\Binn\\;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\Program Files (x86)\\Microsoft SQL Server\\170\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\180\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\170\\DTS\\Binn\\;C:\\Program Files\\Go\\bin;C:\\Program Files\\cursor\\resources\\app\\bin;C:\\Program Files\\Git\\cmd;C:\\Program Files\\dotnet\\;C:\\Users\\user\\AppData\\Local\\Programs\\Python\\Python310\\Scripts\\;C:\\Users\\user\\AppData\\Local\\Programs\\Python\\Python310\\;C:\\Users\\user\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\user\\.dotnet\\tools;C:\\Users\\user\\AppData\\Local\\Programs\\Microsoft VS Code\\bin;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Roaming\\npm;C:\\Users\\user\\.lmstudio\\bin;C:\\Users\\user\\AppData\\Local\\Programs\\Ollama;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Local\\nvm\\Current\\nodejs;C:\\Program Files\\OpenSSL-Win64\\bin\\;G:\\Work\\Tools\\GitClean;C:\\Users\\user\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\user\\AppData\\Local\\Programs\\Antigravity\\bin;C:\\Users\\user\\go\\bin;C:\\Users\\user\\.dotnet\\tools" OLLAMA_NEW_ESTIMATES=1 OLLAMA_FLASH_ATTENTION=1 OLLAMA_HOST=0.0.0.0 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_NEW_ENGINE=1 OLLAMA_DEBUG=1 OLLAMA_NUM_PARALLEL=2 OLLAMA_LIBRARY_PATH=C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13
time=2026-02-06T11:03:16.177+01:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=667.023ms 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=2026-02-06T11:03:16.178+01:00 level=INFO source=server.go:430 msg="starting runner" cmd="C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62308"
time=2026-02-06T11:03:16.178+01:00 level=DEBUG source=server.go:431 msg=subprocess OLLAMA_MODELS=C:\Ollama\models PATH="C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\java8path;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\javapath;C:\\Program Files\\Microsoft SDKs\\Azure\\CLI2\\wbin;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\Program Files\\NVIDIA Corporation\\NVIDIA app\\NvDLISR;C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common;C:\\Program Files\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\170\\Tools\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\160\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\160\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\160\\DTS\\Binn\\;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Local\\nvm\\Current\\nodejs;C:\\Program Files\\Certbot\\bin;C:\\Program Files\\FirefoxPWA\\;C:\\Program Files\\Microsoft SQL Server\\170\\Tools\\Binn\\;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\Program Files (x86)\\Microsoft SQL Server\\170\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\180\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\170\\DTS\\Binn\\;C:\\Program Files\\Go\\bin;C:\\Program Files\\cursor\\resources\\app\\bin;C:\\Program Files\\Git\\cmd;C:\\Program Files\\dotnet\\;C:\\Users\\user\\AppData\\Local\\Programs\\Python\\Python310\\Scripts\\;C:\\Users\\user\\AppData\\Local\\Programs\\Python\\Python310\\;C:\\Users\\user\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\user\\.dotnet\\tools;C:\\Users\\user\\AppData\\Local\\Programs\\Microsoft VS Code\\bin;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Roaming\\npm;C:\\Users\\user\\.lmstudio\\bin;C:\\Users\\user\\AppData\\Local\\Programs\\Ollama;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Local\\nvm\\Current\\nodejs;C:\\Program Files\\OpenSSL-Win64\\bin\\;G:\\Work\\Tools\\GitClean;C:\\Users\\user\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\user\\AppData\\Local\\Programs\\Antigravity\\bin;C:\\Users\\user\\go\\bin;C:\\Users\\user\\.dotnet\\tools" OLLAMA_NEW_ESTIMATES=1 OLLAMA_FLASH_ATTENTION=1 OLLAMA_HOST=0.0.0.0 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_NEW_ENGINE=1 OLLAMA_DEBUG=1 OLLAMA_NUM_PARALLEL=2 OLLAMA_LIBRARY_PATH=C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama\rocm
time=2026-02-06T11:03:16.478+01:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=300.6419ms 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=2026-02-06T11:03:16.478+01:00 level=INFO source=runner.go:106 msg="experimental Vulkan support disabled.  To enable, set OLLAMA_VULKAN=1"
time=2026-02-06T11:03:16.478+01:00 level=DEBUG source=runner.go:124 msg="evaluating which, if any, devices to filter out" initial_count=2
time=2026-02-06T11:03:16.478+01:00 level=DEBUG source=runner.go:146 msg="verifying if device is supported" library=C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12 description="NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition" compute=12.0 id=GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa pci_id=0000:02:00.0
time=2026-02-06T11:03:16.478+01:00 level=DEBUG source=runner.go:146 msg="verifying if device is supported" library=C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13 description="NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition" compute=12.0 id=GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa pci_id=0000:02:00.0
time=2026-02-06T11:03:16.480+01:00 level=INFO source=server.go:430 msg="starting runner" cmd="C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62315"
time=2026-02-06T11:03:16.480+01:00 level=INFO source=server.go:430 msg="starting runner" cmd="C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62316"
time=2026-02-06T11:03:16.480+01:00 level=DEBUG source=server.go:431 msg=subprocess OLLAMA_MODELS=C:\Ollama\models PATH="C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\java8path;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\javapath;C:\\Program Files\\Microsoft SDKs\\Azure\\CLI2\\wbin;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\Program Files\\NVIDIA Corporation\\NVIDIA app\\NvDLISR;C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common;C:\\Program Files\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\170\\Tools\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\160\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\160\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\160\\DTS\\Binn\\;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Local\\nvm\\Current\\nodejs;C:\\Program Files\\Certbot\\bin;C:\\Program Files\\FirefoxPWA\\;C:\\Program Files\\Microsoft SQL Server\\170\\Tools\\Binn\\;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\Program Files (x86)\\Microsoft SQL Server\\170\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\180\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\170\\DTS\\Binn\\;C:\\Program Files\\Go\\bin;C:\\Program Files\\cursor\\resources\\app\\bin;C:\\Program Files\\Git\\cmd;C:\\Program Files\\dotnet\\;C:\\Users\\user\\AppData\\Local\\Programs\\Python\\Python310\\Scripts\\;C:\\Users\\user\\AppData\\Local\\Programs\\Python\\Python310\\;C:\\Users\\user\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\user\\.dotnet\\tools;C:\\Users\\user\\AppData\\Local\\Programs\\Microsoft VS Code\\bin;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Roaming\\npm;C:\\Users\\user\\.lmstudio\\bin;C:\\Users\\user\\AppData\\Local\\Programs\\Ollama;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Local\\nvm\\Current\\nodejs;C:\\Program Files\\OpenSSL-Win64\\bin\\;G:\\Work\\Tools\\GitClean;C:\\Users\\user\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\user\\AppData\\Local\\Programs\\Antigravity\\bin;C:\\Users\\user\\go\\bin;C:\\Users\\user\\.dotnet\\tools" OLLAMA_NEW_ESTIMATES=1 OLLAMA_FLASH_ATTENTION=1 OLLAMA_HOST=0.0.0.0 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_NEW_ENGINE=1 OLLAMA_DEBUG=1 OLLAMA_NUM_PARALLEL=2 OLLAMA_LIBRARY_PATH=C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12 GGML_CUDA_INIT=1 CUDA_VISIBLE_DEVICES=GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa
time=2026-02-06T11:03:16.480+01:00 level=DEBUG source=server.go:431 msg=subprocess OLLAMA_MODELS=C:\Ollama\models PATH="C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\java8path;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\javapath;C:\\Program Files\\Microsoft SDKs\\Azure\\CLI2\\wbin;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\Program Files\\NVIDIA Corporation\\NVIDIA app\\NvDLISR;C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common;C:\\Program Files\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\170\\Tools\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\160\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\160\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\160\\DTS\\Binn\\;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Local\\nvm\\Current\\nodejs;C:\\Program Files\\Certbot\\bin;C:\\Program Files\\FirefoxPWA\\;C:\\Program Files\\Microsoft SQL Server\\170\\Tools\\Binn\\;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\Program Files (x86)\\Microsoft SQL Server\\170\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\180\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\170\\DTS\\Binn\\;C:\\Program Files\\Go\\bin;C:\\Program Files\\cursor\\resources\\app\\bin;C:\\Program Files\\Git\\cmd;C:\\Program Files\\dotnet\\;C:\\Users\\user\\AppData\\Local\\Programs\\Python\\Python310\\Scripts\\;C:\\Users\\user\\AppData\\Local\\Programs\\Python\\Python310\\;C:\\Users\\user\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\user\\.dotnet\\tools;C:\\Users\\user\\AppData\\Local\\Programs\\Microsoft VS Code\\bin;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Roaming\\npm;C:\\Users\\user\\.lmstudio\\bin;C:\\Users\\user\\AppData\\Local\\Programs\\Ollama;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Local\\nvm\\Current\\nodejs;C:\\Program Files\\OpenSSL-Win64\\bin\\;G:\\Work\\Tools\\GitClean;C:\\Users\\user\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\user\\AppData\\Local\\Programs\\Antigravity\\bin;C:\\Users\\user\\go\\bin;C:\\Users\\user\\.dotnet\\tools" OLLAMA_NEW_ESTIMATES=1 OLLAMA_FLASH_ATTENTION=1 OLLAMA_HOST=0.0.0.0 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_NEW_ENGINE=1 OLLAMA_DEBUG=1 OLLAMA_NUM_PARALLEL=2 OLLAMA_LIBRARY_PATH=C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13 GGML_CUDA_INIT=1 CUDA_VISIBLE_DEVICES=GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa
time=2026-02-06T11:03:16.721+01:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=242.667ms 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[CUDA_VISIBLE_DEVICES:GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa GGML_CUDA_INIT:1]"
time=2026-02-06T11:03:16.721+01:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=242.667ms 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[CUDA_VISIBLE_DEVICES:GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa GGML_CUDA_INIT:1]"
time=2026-02-06T11:03:16.721+01:00 level=DEBUG source=runner.go:401 msg="filtering device with overlapping libraries" id=GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa library=C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12 delete_index=0 kept_library=C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13
time=2026-02-06T11:03:16.721+01:00 level=DEBUG source=runner.go:40 msg="GPU bootstrap discovery took" duration=4.4580641s
time=2026-02-06T11:03:16.721+01:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa filter_id="" library=CUDA compute=12.0 name=CUDA0 description="NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition" libdirs=ollama,cuda_v13 driver=13.0 pci_id=0000:02:00.0 type=discrete total="95.6 GiB" available="94.2 GiB"
time=2026-02-06T11:03:16.721+01:00 level=INFO source=routes.go:1739 msg="vram-based default context" total_vram="95.6 GiB" default_num_ctx=262144
[GIN] 2026/02/06 - 11:03:16 | 200 |       514.5µs |       127.0.0.1 | GET      "/api/version"
[GIN] 2026/02/06 - 11:03:16 | 200 |       514.5µs |       127.0.0.1 | GET      "/api/version"
[GIN] 2026/02/06 - 11:03:16 | 200 |       514.5µs |             ::1 | GET      "/api/ps"
[GIN] 2026/02/06 - 11:03:16 | 200 |            0s |       127.0.0.1 | GET      "/api/version"
time=2026-02-06T11:03:16.833+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=general.alignment default=32
[GIN] 2026/02/06 - 11:03:16 | 200 |    112.4703ms |       127.0.0.1 | POST     "/api/show"
[GIN] 2026/02/06 - 11:03:16 | 200 |    158.9248ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/06 - 11:03:16 | 401 |     193.783ms |       127.0.0.1 | POST     "/api/me"
[GIN] 2026/02/06 - 11:03:16 | 401 |    196.6958ms |       127.0.0.1 | POST     "/api/me"
time=2026-02-06T11:03:19.481+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=general.alignment default=32
[GIN] 2026/02/06 - 11:03:19 | 200 |     31.5233ms |       127.0.0.1 | POST     "/api/show"
[GIN] 2026/02/06 - 11:03:34 | 200 |      8.8323ms |       127.0.0.1 | GET      "/api/tags"
time=2026-02-06T11:03:34.725+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=general.alignment default=32
[GIN] 2026/02/06 - 11:03:34 | 200 |     35.6257ms |       127.0.0.1 | POST     "/api/show"
time=2026-02-06T11:03:34.757+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=general.alignment default=32
[GIN] 2026/02/06 - 11:03:34 | 200 |     31.2315ms |       127.0.0.1 | POST     "/api/show"
time=2026-02-06T11:03:34.806+01:00 level=DEBUG source=runner.go:264 msg="refreshing free memory"
time=2026-02-06T11:03:34.807+01:00 level=DEBUG source=runner.go:328 msg="unable to refresh all GPUs with existing runners, performing bootstrap discovery"
time=2026-02-06T11:03:34.808+01:00 level=INFO source=server.go:430 msg="starting runner" cmd="C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 56820"
time=2026-02-06T11:03:34.808+01:00 level=DEBUG source=server.go:431 msg=subprocess OLLAMA_MODELS=C:\Ollama\models PATH="C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\java8path;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\javapath;C:\\Program Files\\Microsoft SDKs\\Azure\\CLI2\\wbin;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\Program Files\\NVIDIA Corporation\\NVIDIA app\\NvDLISR;C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common;C:\\Program Files\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\170\\Tools\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\160\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\160\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\160\\DTS\\Binn\\;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Local\\nvm\\Current\\nodejs;C:\\Program Files\\Certbot\\bin;C:\\Program Files\\FirefoxPWA\\;C:\\Program Files\\Microsoft SQL Server\\170\\Tools\\Binn\\;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\Program Files (x86)\\Microsoft SQL Server\\170\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\180\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\170\\DTS\\Binn\\;C:\\Program Files\\Go\\bin;C:\\Program Files\\cursor\\resources\\app\\bin;C:\\Program Files\\Git\\cmd;C:\\Program Files\\dotnet\\;C:\\Users\\user\\AppData\\Local\\Programs\\Python\\Python310\\Scripts\\;C:\\Users\\user\\AppData\\Local\\Programs\\Python\\Python310\\;C:\\Users\\user\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\user\\.dotnet\\tools;C:\\Users\\user\\AppData\\Local\\Programs\\Microsoft VS Code\\bin;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Roaming\\npm;C:\\Users\\user\\.lmstudio\\bin;C:\\Users\\user\\AppData\\Local\\Programs\\Ollama;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Local\\nvm\\Current\\nodejs;C:\\Program Files\\OpenSSL-Win64\\bin\\;G:\\Work\\Tools\\GitClean;C:\\Users\\user\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\user\\AppData\\Local\\Programs\\Antigravity\\bin;C:\\Users\\user\\go\\bin;C:\\Users\\user\\.dotnet\\tools" OLLAMA_NEW_ESTIMATES=1 OLLAMA_FLASH_ATTENTION=1 OLLAMA_HOST=0.0.0.0 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_NEW_ENGINE=1 OLLAMA_DEBUG=1 OLLAMA_NUM_PARALLEL=2 OLLAMA_LIBRARY_PATH=C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13
time=2026-02-06T11:03:35.007+01:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=199.8032ms 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=2026-02-06T11:03:35.007+01:00 level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=200.3105ms
time=2026-02-06T11:03:35.007+01:00 level=INFO source=cpu_windows.go:148 msg=packages count=1
time=2026-02-06T11:03:35.007+01:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1
time=2026-02-06T11:03:35.007+01:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=20 efficiency=12 threads=20
time=2026-02-06T11:03:35.007+01:00 level=DEBUG source=sched.go:195 msg="updating default concurrency" OLLAMA_MAX_LOADED_MODELS=3 gpu_count=1
time=2026-02-06T11:03:35.010+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=general.alignment default=32
time=2026-02-06T11:03:35.011+01:00 level=DEBUG source=sched.go:231 msg="loading first model" model=C:\Ollama\models\blobs\sha256-65493e1f85b9ea4ba3ed793515fde13cbdbea7d74ad2c662b566b146eab0081e
time=2026-02-06T11:03:35.026+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=general.alignment default=32
time=2026-02-06T11:03:35.026+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=glmocr.pooling_type default=0
time=2026-02-06T11:03:35.026+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=false
time=2026-02-06T11:03:35.026+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
time=2026-02-06T11:03:35.026+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=glmocr.rope.dimension_count default=128
time=2026-02-06T11:03:35.026+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=glmocr.vision.num_channels default=3
time=2026-02-06T11:03:35.026+01:00 level=INFO source=server.go:246 msg="enabling flash attention"
time=2026-02-06T11:03:35.027+01:00 level=INFO source=server.go:430 msg="starting runner" cmd="C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model C:\\Ollama\\models\\blobs\\sha256-65493e1f85b9ea4ba3ed793515fde13cbdbea7d74ad2c662b566b146eab0081e --port 56827"
time=2026-02-06T11:03:35.027+01:00 level=DEBUG source=server.go:431 msg=subprocess OLLAMA_MODELS=C:\Ollama\models PATH="C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\java8path;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\javapath;C:\\Program Files\\Microsoft SDKs\\Azure\\CLI2\\wbin;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\Program Files\\NVIDIA Corporation\\NVIDIA app\\NvDLISR;C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common;C:\\Program Files\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\170\\Tools\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\160\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\160\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\160\\DTS\\Binn\\;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Local\\nvm\\Current\\nodejs;C:\\Program Files\\Certbot\\bin;C:\\Program Files\\FirefoxPWA\\;C:\\Program Files\\Microsoft SQL Server\\170\\Tools\\Binn\\;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\Program Files (x86)\\Microsoft SQL Server\\170\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\180\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\170\\DTS\\Binn\\;C:\\Program Files\\Go\\bin;C:\\Program Files\\cursor\\resources\\app\\bin;C:\\Program Files\\Git\\cmd;C:\\Program Files\\dotnet\\;C:\\Users\\user\\AppData\\Local\\Programs\\Python\\Python310\\Scripts\\;C:\\Users\\user\\AppData\\Local\\Programs\\Python\\Python310\\;C:\\Users\\user\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\user\\.dotnet\\tools;C:\\Users\\user\\AppData\\Local\\Programs\\Microsoft VS Code\\bin;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Roaming\\npm;C:\\Users\\user\\.lmstudio\\bin;C:\\Users\\user\\AppData\\Local\\Programs\\Ollama;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Local\\nvm\\Current\\nodejs;C:\\Program Files\\OpenSSL-Win64\\bin\\;G:\\Work\\Tools\\GitClean;C:\\Users\\user\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\user\\AppData\\Local\\Programs\\Antigravity\\bin;C:\\Users\\user\\go\\bin;C:\\Users\\user\\.dotnet\\tools" OLLAMA_NEW_ESTIMATES=1 OLLAMA_FLASH_ATTENTION=1 OLLAMA_HOST=0.0.0.0 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_NEW_ENGINE=1 OLLAMA_DEBUG=1 OLLAMA_NUM_PARALLEL=2 OLLAMA_LIBRARY_PATH=C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13
time=2026-02-06T11:03:35.030+01:00 level=INFO source=sched.go:463 msg="system memory" total="63.3 GiB" free="39.5 GiB" free_swap="72.5 GiB"
time=2026-02-06T11:03:35.030+01:00 level=INFO source=sched.go:470 msg="gpu memory" id=GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa library=CUDA available="93.7 GiB" free="94.2 GiB" minimum="457.0 MiB" overhead="0 B"
time=2026-02-06T11:03:35.030+01:00 level=INFO source=server.go:756 msg="loading model" "model layers"=17 requested=-1
time=2026-02-06T11:03:35.081+01:00 level=INFO source=runner.go:1410 msg="starting ollama engine"
time=2026-02-06T11:03:35.083+01:00 level=INFO source=runner.go:1445 msg="Server listening on 127.0.0.1:56827"
time=2026-02-06T11:03:35.084+01:00 level=INFO source=runner.go:1283 msg=load request="{Operation:fit LoraPath:[] Parallel:2 BatchSize:512 FlashAttention:Enabled KvSize:8192 KvCacheType: NumThreads:8 GPULayers:17[ID:GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa Layers:17(0..16)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-02-06T11:03:35.092+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=general.alignment default=32
time=2026-02-06T11:03:35.092+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=general.name default=""
time=2026-02-06T11:03:35.092+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=general.description default=""
time=2026-02-06T11:03:35.092+01:00 level=INFO source=ggml.go:136 msg="" architecture=glmocr file_type=F16 name="" description="" num_tensors=527 num_key_values=47
time=2026-02-06T11:03:35.092+01:00 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-alderlake.dll
time=2026-02-06T11:03:35.102+01:00 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: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
  Device 0: NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition, compute capability 12.0, VMM: yes, ID: GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa
load_backend: loaded CUDA backend from C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13\ggml-cuda.dll
time=2026-02-06T11:03:35.194+01:00 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=2026-02-06T11:03:35.196+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=glmocr.pooling_type default=0
time=2026-02-06T11:03:35.196+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=false
time=2026-02-06T11:03:35.196+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
time=2026-02-06T11:03:35.196+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=glmocr.rope.dimension_count default=128
time=2026-02-06T11:03:35.196+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=glmocr.vision.num_channels default=3
time=2026-02-06T11:03:43.047+01:00 level=DEBUG source=ggml.go:852 msg="compute graph" nodes=940 splits=1
time=2026-02-06T11:03:47.860+01:00 level=DEBUG source=ggml.go:852 msg="compute graph" nodes=586 splits=2
time=2026-02-06T11:03:54.233+01:00 level=DEBUG source=ggml.go:852 msg="compute graph" nodes=584 splits=2
time=2026-02-06T11:03:54.233+01:00 level=DEBUG source=device.go:240 msg="model weights" device=CUDA0 size="1.9 GiB"
time=2026-02-06T11:03:54.233+01:00 level=DEBUG source=device.go:245 msg="model weights" device=CPU size="174.0 MiB"
time=2026-02-06T11:03:54.233+01:00 level=DEBUG source=device.go:251 msg="kv cache" device=CUDA0 size="512.0 MiB"
time=2026-02-06T11:03:54.233+01:00 level=DEBUG source=device.go:262 msg="compute graph" device=CUDA0 size="1.4 GiB"
time=2026-02-06T11:03:54.233+01:00 level=DEBUG source=device.go:267 msg="compute graph" device=CPU size="31.2 MiB"
time=2026-02-06T11:03:54.233+01:00 level=DEBUG source=device.go:272 msg="total memory" size="3.9 GiB"
time=2026-02-06T11:03:54.233+01:00 level=DEBUG source=server.go:781 msg=memory success=true required.InputWeights=182452224 required.CPU.Graph=32741376 required.CUDA0.ID=GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa required.CUDA0.Weights="[61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 1051455488]" required.CUDA0.Cache="[33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 0]" required.CUDA0.Graph=1455846912
time=2026-02-06T11:03:54.233+01:00 level=DEBUG source=server.go:975 msg="available gpu" id=GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa library=CUDA "available layer vram"="92.3 GiB" backoff=0.00 minimum="457.0 MiB" overhead="0 B" graph="1.4 GiB"
time=2026-02-06T11:03:54.233+01:00 level=DEBUG source=server.go:792 msg="new layout created" layers="17[ID:GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa Layers:17(0..16)]"
time=2026-02-06T11:03:54.233+01:00 level=INFO source=runner.go:1283 msg=load request="{Operation:alloc LoraPath:[] Parallel:2 BatchSize:512 FlashAttention:Enabled KvSize:8192 KvCacheType: NumThreads:8 GPULayers:17[ID:GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa Layers:17(0..16)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-02-06T11:03:54.240+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=general.alignment default=32
time=2026-02-06T11:03:54.243+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=glmocr.pooling_type default=0
time=2026-02-06T11:03:54.243+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=false
time=2026-02-06T11:03:54.243+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
time=2026-02-06T11:03:54.243+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=glmocr.rope.dimension_count default=128
time=2026-02-06T11:03:54.243+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=glmocr.vision.num_channels default=3
time=2026-02-06T11:03:54.529+01:00 level=DEBUG source=ggml.go:852 msg="compute graph" nodes=940 splits=1
time=2026-02-06T11:03:54.651+01:00 level=DEBUG source=ggml.go:852 msg="compute graph" nodes=586 splits=2
time=2026-02-06T11:03:54.661+01:00 level=DEBUG source=ggml.go:852 msg="compute graph" nodes=584 splits=2
time=2026-02-06T11:03:54.661+01:00 level=DEBUG source=device.go:240 msg="model weights" device=CUDA0 size="1.9 GiB"
time=2026-02-06T11:03:54.661+01:00 level=DEBUG source=device.go:245 msg="model weights" device=CPU size="174.0 MiB"
time=2026-02-06T11:03:54.661+01:00 level=DEBUG source=device.go:251 msg="kv cache" device=CUDA0 size="512.0 MiB"
time=2026-02-06T11:03:54.661+01:00 level=DEBUG source=device.go:262 msg="compute graph" device=CUDA0 size="1.4 GiB"
time=2026-02-06T11:03:54.661+01:00 level=DEBUG source=device.go:267 msg="compute graph" device=CPU size="31.2 MiB"
time=2026-02-06T11:03:54.661+01:00 level=DEBUG source=device.go:272 msg="total memory" size="3.9 GiB"
time=2026-02-06T11:03:54.661+01:00 level=DEBUG source=server.go:781 msg=memory success=true required.InputWeights=182452224 required.CPU.Graph=32741376 required.CUDA0.ID=GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa required.CUDA0.Weights="[61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 1051455488]" required.CUDA0.Cache="[33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 0]" required.CUDA0.Graph=1455846912
time=2026-02-06T11:03:54.661+01:00 level=DEBUG source=server.go:975 msg="available gpu" id=GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa library=CUDA "available layer vram"="92.3 GiB" backoff=0.00 minimum="457.0 MiB" overhead="0 B" graph="1.4 GiB"
time=2026-02-06T11:03:54.661+01:00 level=DEBUG source=server.go:792 msg="new layout created" layers="17[ID:GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa Layers:17(0..16)]"
time=2026-02-06T11:03:54.661+01:00 level=INFO source=runner.go:1283 msg=load request="{Operation:commit LoraPath:[] Parallel:2 BatchSize:512 FlashAttention:Enabled KvSize:8192 KvCacheType: NumThreads:8 GPULayers:17[ID:GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa Layers:17(0..16)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-02-06T11:03:54.661+01:00 level=INFO source=ggml.go:482 msg="offloading 16 repeating layers to GPU"
time=2026-02-06T11:03:54.661+01:00 level=INFO source=ggml.go:489 msg="offloading output layer to GPU"
time=2026-02-06T11:03:54.661+01:00 level=INFO source=ggml.go:494 msg="offloaded 17/17 layers to GPU"
time=2026-02-06T11:03:54.661+01:00 level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="1.9 GiB"
time=2026-02-06T11:03:54.661+01:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="174.0 MiB"
time=2026-02-06T11:03:54.661+01:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="512.0 MiB"
time=2026-02-06T11:03:54.661+01:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="1.4 GiB"
time=2026-02-06T11:03:54.661+01:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="31.2 MiB"
time=2026-02-06T11:03:54.661+01:00 level=INFO source=device.go:272 msg="total memory" size="3.9 GiB"
time=2026-02-06T11:03:54.661+01:00 level=INFO source=sched.go:537 msg="loaded runners" count=1
time=2026-02-06T11:03:54.661+01:00 level=INFO source=server.go:1349 msg="waiting for llama runner to start responding"
time=2026-02-06T11:03:54.661+01:00 level=INFO source=server.go:1383 msg="waiting for server to become available" status="llm server loading model"
time=2026-02-06T11:03:54.912+01:00 level=DEBUG source=server.go:1393 msg="model load progress 0.13"
time=2026-02-06T11:03:55.162+01:00 level=DEBUG source=server.go:1393 msg="model load progress 0.27"
time=2026-02-06T11:03:55.412+01:00 level=DEBUG source=server.go:1393 msg="model load progress 0.43"
time=2026-02-06T11:03:55.663+01:00 level=DEBUG source=server.go:1393 msg="model load progress 0.64"
time=2026-02-06T11:03:55.913+01:00 level=DEBUG source=server.go:1393 msg="model load progress 0.78"
time=2026-02-06T11:03:56.163+01:00 level=DEBUG source=server.go:1393 msg="model load progress 0.92"
time=2026-02-06T11:03:56.389+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=glmocr.pooling_type default=0
time=2026-02-06T11:03:56.414+01:00 level=INFO source=server.go:1387 msg="llama runner started in 21.38 seconds"
time=2026-02-06T11:03:56.414+01:00 level=DEBUG source=sched.go:549 msg="finished setting up" runner.name=registry.ollama.ai/library/glm-ocr:latest runner.inference="[{ID:GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa Library:CUDA}]" runner.size="3.9 GiB" runner.vram="3.9 GiB" runner.parallel=2 runner.pid=2148 runner.model=C:\Ollama\models\blobs\sha256-65493e1f85b9ea4ba3ed793515fde13cbdbea7d74ad2c662b566b146eab0081e runner.num_ctx=4096
time=2026-02-06T11:03:56.422+01:00 level=DEBUG source=server.go:1535 msg="completion request" images=1 prompt=45 format=""
time=2026-02-06T11:03:56.524+01:00 level=DEBUG source=cache.go:151 msg="loading cache slot" id=0 cache=0 prompt=1102 used=0 remaining=1102
time=2026-02-06T11:04:04.085+01:00 level=DEBUG source=server.go:1661 msg="prediction aborted, token repeat limit reached"
[GIN] 2026/02/06 - 11:04:04 | 200 |   29.3258245s |       127.0.0.1 | POST     "/api/chat"
time=2026-02-06T11:04:04.085+01:00 level=DEBUG source=sched.go:557 msg="context for request finished"
time=2026-02-06T11:04:04.085+01:00 level=DEBUG source=sched.go:310 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/glm-ocr:latest runner.inference="[{ID:GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa Library:CUDA}]" runner.size="3.9 GiB" runner.vram="3.9 GiB" runner.parallel=2 runner.pid=2148 runner.model=C:\Ollama\models\blobs\sha256-65493e1f85b9ea4ba3ed793515fde13cbdbea7d74ad2c662b566b146eab0081e runner.num_ctx=4096 duration=5m0s
time=2026-02-06T11:04:04.085+01:00 level=DEBUG source=sched.go:328 msg="after processing request finished event" runner.name=registry.ollama.ai/library/glm-ocr:latest runner.inference="[{ID:GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa Library:CUDA}]" runner.size="3.9 GiB" runner.vram="3.9 GiB" runner.parallel=2 runner.pid=2148 runner.model=C:\Ollama\models\blobs\sha256-65493e1f85b9ea4ba3ed793515fde13cbdbea7d74ad2c662b566b146eab0081e runner.num_ctx=4096 refCount=0
[GIN] 2026/02/06 - 11:04:04 | 200 |      5.8562ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/06 - 11:04:13 | 200 |       354.2µs |             ::1 | GET      "/api/ps"

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.15.5

Originally created by @illusdolphin on GitHub (Feb 6, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14117 ### What is the issue? Ollama stops on this image, while others works fine. Expected to have more text (see image to see that this is only 1 item from many on image). Expected: text is extracted after "......". Actually: it stops. Ollama: latest 0.15.5 Windows (latest) GPU: RTX 6000 pro max-Q 96GB VRAM Request resulted in (via API or CLI result is the same): ``` { "model": "glm-ocr:latest", "created_at": "2026-02-06T10:01:23.4538287Z", "message": { "role": "assistant", "content": "IV. Podane w nawiasie przymiotniki proszę przekształcić na stopień najwyższy.\nPrzyklad: Ta ulica jest (szeroka) najszersza w naszym mieście.\n1. To jest (elegancki) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ." }, "done": false } ``` **POST /api/chat** ``` { "model": "glm-ocr:latest", "stream": false, "options": { "num_ctx": 8196 }, "messages": [ { "role": "user", "content": "OCR <image>", "images": ["base64"] } ] } ``` Image 1180x721 below (not too big, but attached as file to avoid huge base64 text): <img width="590" height="360" alt="Image" src="https://github.com/user-attachments/assets/1a84337b-f98c-49de-a788-43731d064c30" /> The same result when using CLI: `ollama run glm-ocr Text Recognition: ./image.png` From logs I see that ollama reaches some limit, but it looks like an issue: `time=2026-02-06T11:04:04.085+01:00 level=DEBUG source=server.go:1661 msg="prediction aborted, token repeat limit reached"` What did I try: * Reduce OLLAMA_NUM_PARALLEL to 1 * Remove OLLAMA_FLASH_ATTENTION, OLLAMA_NEW_ENGINE, OLLAMA_NEW_ESTIMATES * Increase context length (up to ~40k, at ~80k ollama fails to process request) * Change image proportions * Change prompt ### Relevant log output ```shell time=2026-02-06T11:03:12.238+01:00 level=INFO source=routes.go:1636 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 OLLAMA_FLASH_ATTENTION:true OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 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:C:\\Ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:true OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:2 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=2026-02-06T11:03:12.253+01:00 level=INFO source=images.go:473 msg="total blobs: 173" time=2026-02-06T11:03:12.258+01:00 level=INFO source=images.go:480 msg="total unused blobs removed: 0" time=2026-02-06T11:03:12.262+01:00 level=INFO source=routes.go:1689 msg="Listening on [::]:11434 (version 0.15.5)" time=2026-02-06T11:03:12.263+01:00 level=DEBUG source=sched.go:121 msg="starting llm scheduler" time=2026-02-06T11:03:12.264+01:00 level=INFO source=runner.go:67 msg="discovering available GPUs..." time=2026-02-06T11:03:12.276+01:00 level=INFO source=server.go:430 msg="starting runner" cmd="C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 52100" time=2026-02-06T11:03:12.277+01:00 level=DEBUG source=server.go:431 msg=subprocess OLLAMA_MODELS=C:\Ollama\models PATH="C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\java8path;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\javapath;C:\\Program Files\\Microsoft SDKs\\Azure\\CLI2\\wbin;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\Program Files\\NVIDIA Corporation\\NVIDIA app\\NvDLISR;C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common;C:\\Program Files\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\170\\Tools\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\160\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\160\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\160\\DTS\\Binn\\;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Local\\nvm\\Current\\nodejs;C:\\Program Files\\Certbot\\bin;C:\\Program Files\\FirefoxPWA\\;C:\\Program Files\\Microsoft SQL Server\\170\\Tools\\Binn\\;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\Program Files (x86)\\Microsoft SQL Server\\170\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\180\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\170\\DTS\\Binn\\;C:\\Program Files\\Go\\bin;C:\\Program Files\\cursor\\resources\\app\\bin;C:\\Program Files\\Git\\cmd;C:\\Program Files\\dotnet\\;C:\\Users\\user\\AppData\\Local\\Programs\\Python\\Python310\\Scripts\\;C:\\Users\\user\\AppData\\Local\\Programs\\Python\\Python310\\;C:\\Users\\user\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\user\\.dotnet\\tools;C:\\Users\\user\\AppData\\Local\\Programs\\Microsoft VS Code\\bin;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Roaming\\npm;C:\\Users\\user\\.lmstudio\\bin;C:\\Users\\user\\AppData\\Local\\Programs\\Ollama;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Local\\nvm\\Current\\nodejs;C:\\Program Files\\OpenSSL-Win64\\bin\\;G:\\Work\\Tools\\GitClean;C:\\Users\\user\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\user\\AppData\\Local\\Programs\\Antigravity\\bin;C:\\Users\\user\\go\\bin;C:\\Users\\user\\.dotnet\\tools" OLLAMA_NEW_ESTIMATES=1 OLLAMA_FLASH_ATTENTION=1 OLLAMA_HOST=0.0.0.0 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_NEW_ENGINE=1 OLLAMA_DEBUG=1 OLLAMA_NUM_PARALLEL=2 OLLAMA_LIBRARY_PATH=C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12 time=2026-02-06T11:03:15.510+01:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=3.2398578s 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=2026-02-06T11:03:15.511+01:00 level=INFO source=server.go:430 msg="starting runner" cmd="C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62301" time=2026-02-06T11:03:15.511+01:00 level=DEBUG source=server.go:431 msg=subprocess OLLAMA_MODELS=C:\Ollama\models PATH="C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\java8path;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\javapath;C:\\Program Files\\Microsoft SDKs\\Azure\\CLI2\\wbin;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\Program Files\\NVIDIA Corporation\\NVIDIA app\\NvDLISR;C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common;C:\\Program Files\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\170\\Tools\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\160\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\160\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\160\\DTS\\Binn\\;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Local\\nvm\\Current\\nodejs;C:\\Program Files\\Certbot\\bin;C:\\Program Files\\FirefoxPWA\\;C:\\Program Files\\Microsoft SQL Server\\170\\Tools\\Binn\\;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\Program Files (x86)\\Microsoft SQL Server\\170\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\180\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\170\\DTS\\Binn\\;C:\\Program Files\\Go\\bin;C:\\Program Files\\cursor\\resources\\app\\bin;C:\\Program Files\\Git\\cmd;C:\\Program Files\\dotnet\\;C:\\Users\\user\\AppData\\Local\\Programs\\Python\\Python310\\Scripts\\;C:\\Users\\user\\AppData\\Local\\Programs\\Python\\Python310\\;C:\\Users\\user\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\user\\.dotnet\\tools;C:\\Users\\user\\AppData\\Local\\Programs\\Microsoft VS Code\\bin;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Roaming\\npm;C:\\Users\\user\\.lmstudio\\bin;C:\\Users\\user\\AppData\\Local\\Programs\\Ollama;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Local\\nvm\\Current\\nodejs;C:\\Program Files\\OpenSSL-Win64\\bin\\;G:\\Work\\Tools\\GitClean;C:\\Users\\user\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\user\\AppData\\Local\\Programs\\Antigravity\\bin;C:\\Users\\user\\go\\bin;C:\\Users\\user\\.dotnet\\tools" OLLAMA_NEW_ESTIMATES=1 OLLAMA_FLASH_ATTENTION=1 OLLAMA_HOST=0.0.0.0 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_NEW_ENGINE=1 OLLAMA_DEBUG=1 OLLAMA_NUM_PARALLEL=2 OLLAMA_LIBRARY_PATH=C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13 time=2026-02-06T11:03:16.177+01:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=667.023ms 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=2026-02-06T11:03:16.178+01:00 level=INFO source=server.go:430 msg="starting runner" cmd="C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62308" time=2026-02-06T11:03:16.178+01:00 level=DEBUG source=server.go:431 msg=subprocess OLLAMA_MODELS=C:\Ollama\models PATH="C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\java8path;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\javapath;C:\\Program Files\\Microsoft SDKs\\Azure\\CLI2\\wbin;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\Program Files\\NVIDIA Corporation\\NVIDIA app\\NvDLISR;C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common;C:\\Program Files\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\170\\Tools\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\160\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\160\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\160\\DTS\\Binn\\;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Local\\nvm\\Current\\nodejs;C:\\Program Files\\Certbot\\bin;C:\\Program Files\\FirefoxPWA\\;C:\\Program Files\\Microsoft SQL Server\\170\\Tools\\Binn\\;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\Program Files (x86)\\Microsoft SQL Server\\170\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\180\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\170\\DTS\\Binn\\;C:\\Program Files\\Go\\bin;C:\\Program Files\\cursor\\resources\\app\\bin;C:\\Program Files\\Git\\cmd;C:\\Program Files\\dotnet\\;C:\\Users\\user\\AppData\\Local\\Programs\\Python\\Python310\\Scripts\\;C:\\Users\\user\\AppData\\Local\\Programs\\Python\\Python310\\;C:\\Users\\user\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\user\\.dotnet\\tools;C:\\Users\\user\\AppData\\Local\\Programs\\Microsoft VS Code\\bin;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Roaming\\npm;C:\\Users\\user\\.lmstudio\\bin;C:\\Users\\user\\AppData\\Local\\Programs\\Ollama;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Local\\nvm\\Current\\nodejs;C:\\Program Files\\OpenSSL-Win64\\bin\\;G:\\Work\\Tools\\GitClean;C:\\Users\\user\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\user\\AppData\\Local\\Programs\\Antigravity\\bin;C:\\Users\\user\\go\\bin;C:\\Users\\user\\.dotnet\\tools" OLLAMA_NEW_ESTIMATES=1 OLLAMA_FLASH_ATTENTION=1 OLLAMA_HOST=0.0.0.0 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_NEW_ENGINE=1 OLLAMA_DEBUG=1 OLLAMA_NUM_PARALLEL=2 OLLAMA_LIBRARY_PATH=C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama\rocm time=2026-02-06T11:03:16.478+01:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=300.6419ms 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=2026-02-06T11:03:16.478+01:00 level=INFO source=runner.go:106 msg="experimental Vulkan support disabled. To enable, set OLLAMA_VULKAN=1" time=2026-02-06T11:03:16.478+01:00 level=DEBUG source=runner.go:124 msg="evaluating which, if any, devices to filter out" initial_count=2 time=2026-02-06T11:03:16.478+01:00 level=DEBUG source=runner.go:146 msg="verifying if device is supported" library=C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12 description="NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition" compute=12.0 id=GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa pci_id=0000:02:00.0 time=2026-02-06T11:03:16.478+01:00 level=DEBUG source=runner.go:146 msg="verifying if device is supported" library=C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13 description="NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition" compute=12.0 id=GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa pci_id=0000:02:00.0 time=2026-02-06T11:03:16.480+01:00 level=INFO source=server.go:430 msg="starting runner" cmd="C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62315" time=2026-02-06T11:03:16.480+01:00 level=INFO source=server.go:430 msg="starting runner" cmd="C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62316" time=2026-02-06T11:03:16.480+01:00 level=DEBUG source=server.go:431 msg=subprocess OLLAMA_MODELS=C:\Ollama\models PATH="C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\java8path;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\javapath;C:\\Program Files\\Microsoft SDKs\\Azure\\CLI2\\wbin;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\Program Files\\NVIDIA Corporation\\NVIDIA app\\NvDLISR;C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common;C:\\Program Files\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\170\\Tools\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\160\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\160\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\160\\DTS\\Binn\\;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Local\\nvm\\Current\\nodejs;C:\\Program Files\\Certbot\\bin;C:\\Program Files\\FirefoxPWA\\;C:\\Program Files\\Microsoft SQL Server\\170\\Tools\\Binn\\;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\Program Files (x86)\\Microsoft SQL Server\\170\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\180\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\170\\DTS\\Binn\\;C:\\Program Files\\Go\\bin;C:\\Program Files\\cursor\\resources\\app\\bin;C:\\Program Files\\Git\\cmd;C:\\Program Files\\dotnet\\;C:\\Users\\user\\AppData\\Local\\Programs\\Python\\Python310\\Scripts\\;C:\\Users\\user\\AppData\\Local\\Programs\\Python\\Python310\\;C:\\Users\\user\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\user\\.dotnet\\tools;C:\\Users\\user\\AppData\\Local\\Programs\\Microsoft VS Code\\bin;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Roaming\\npm;C:\\Users\\user\\.lmstudio\\bin;C:\\Users\\user\\AppData\\Local\\Programs\\Ollama;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Local\\nvm\\Current\\nodejs;C:\\Program Files\\OpenSSL-Win64\\bin\\;G:\\Work\\Tools\\GitClean;C:\\Users\\user\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\user\\AppData\\Local\\Programs\\Antigravity\\bin;C:\\Users\\user\\go\\bin;C:\\Users\\user\\.dotnet\\tools" OLLAMA_NEW_ESTIMATES=1 OLLAMA_FLASH_ATTENTION=1 OLLAMA_HOST=0.0.0.0 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_NEW_ENGINE=1 OLLAMA_DEBUG=1 OLLAMA_NUM_PARALLEL=2 OLLAMA_LIBRARY_PATH=C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12 GGML_CUDA_INIT=1 CUDA_VISIBLE_DEVICES=GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa time=2026-02-06T11:03:16.480+01:00 level=DEBUG source=server.go:431 msg=subprocess OLLAMA_MODELS=C:\Ollama\models PATH="C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\java8path;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\javapath;C:\\Program Files\\Microsoft SDKs\\Azure\\CLI2\\wbin;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\Program Files\\NVIDIA Corporation\\NVIDIA app\\NvDLISR;C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common;C:\\Program Files\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\170\\Tools\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\160\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\160\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\160\\DTS\\Binn\\;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Local\\nvm\\Current\\nodejs;C:\\Program Files\\Certbot\\bin;C:\\Program Files\\FirefoxPWA\\;C:\\Program Files\\Microsoft SQL Server\\170\\Tools\\Binn\\;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\Program Files (x86)\\Microsoft SQL Server\\170\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\180\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\170\\DTS\\Binn\\;C:\\Program Files\\Go\\bin;C:\\Program Files\\cursor\\resources\\app\\bin;C:\\Program Files\\Git\\cmd;C:\\Program Files\\dotnet\\;C:\\Users\\user\\AppData\\Local\\Programs\\Python\\Python310\\Scripts\\;C:\\Users\\user\\AppData\\Local\\Programs\\Python\\Python310\\;C:\\Users\\user\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\user\\.dotnet\\tools;C:\\Users\\user\\AppData\\Local\\Programs\\Microsoft VS Code\\bin;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Roaming\\npm;C:\\Users\\user\\.lmstudio\\bin;C:\\Users\\user\\AppData\\Local\\Programs\\Ollama;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Local\\nvm\\Current\\nodejs;C:\\Program Files\\OpenSSL-Win64\\bin\\;G:\\Work\\Tools\\GitClean;C:\\Users\\user\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\user\\AppData\\Local\\Programs\\Antigravity\\bin;C:\\Users\\user\\go\\bin;C:\\Users\\user\\.dotnet\\tools" OLLAMA_NEW_ESTIMATES=1 OLLAMA_FLASH_ATTENTION=1 OLLAMA_HOST=0.0.0.0 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_NEW_ENGINE=1 OLLAMA_DEBUG=1 OLLAMA_NUM_PARALLEL=2 OLLAMA_LIBRARY_PATH=C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13 GGML_CUDA_INIT=1 CUDA_VISIBLE_DEVICES=GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa time=2026-02-06T11:03:16.721+01:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=242.667ms 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[CUDA_VISIBLE_DEVICES:GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa GGML_CUDA_INIT:1]" time=2026-02-06T11:03:16.721+01:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=242.667ms 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[CUDA_VISIBLE_DEVICES:GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa GGML_CUDA_INIT:1]" time=2026-02-06T11:03:16.721+01:00 level=DEBUG source=runner.go:401 msg="filtering device with overlapping libraries" id=GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa library=C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12 delete_index=0 kept_library=C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13 time=2026-02-06T11:03:16.721+01:00 level=DEBUG source=runner.go:40 msg="GPU bootstrap discovery took" duration=4.4580641s time=2026-02-06T11:03:16.721+01:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa filter_id="" library=CUDA compute=12.0 name=CUDA0 description="NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition" libdirs=ollama,cuda_v13 driver=13.0 pci_id=0000:02:00.0 type=discrete total="95.6 GiB" available="94.2 GiB" time=2026-02-06T11:03:16.721+01:00 level=INFO source=routes.go:1739 msg="vram-based default context" total_vram="95.6 GiB" default_num_ctx=262144 [GIN] 2026/02/06 - 11:03:16 | 200 | 514.5µs | 127.0.0.1 | GET "/api/version" [GIN] 2026/02/06 - 11:03:16 | 200 | 514.5µs | 127.0.0.1 | GET "/api/version" [GIN] 2026/02/06 - 11:03:16 | 200 | 514.5µs | ::1 | GET "/api/ps" [GIN] 2026/02/06 - 11:03:16 | 200 | 0s | 127.0.0.1 | GET "/api/version" time=2026-02-06T11:03:16.833+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=general.alignment default=32 [GIN] 2026/02/06 - 11:03:16 | 200 | 112.4703ms | 127.0.0.1 | POST "/api/show" [GIN] 2026/02/06 - 11:03:16 | 200 | 158.9248ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/06 - 11:03:16 | 401 | 193.783ms | 127.0.0.1 | POST "/api/me" [GIN] 2026/02/06 - 11:03:16 | 401 | 196.6958ms | 127.0.0.1 | POST "/api/me" time=2026-02-06T11:03:19.481+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=general.alignment default=32 [GIN] 2026/02/06 - 11:03:19 | 200 | 31.5233ms | 127.0.0.1 | POST "/api/show" [GIN] 2026/02/06 - 11:03:34 | 200 | 8.8323ms | 127.0.0.1 | GET "/api/tags" time=2026-02-06T11:03:34.725+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=general.alignment default=32 [GIN] 2026/02/06 - 11:03:34 | 200 | 35.6257ms | 127.0.0.1 | POST "/api/show" time=2026-02-06T11:03:34.757+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=general.alignment default=32 [GIN] 2026/02/06 - 11:03:34 | 200 | 31.2315ms | 127.0.0.1 | POST "/api/show" time=2026-02-06T11:03:34.806+01:00 level=DEBUG source=runner.go:264 msg="refreshing free memory" time=2026-02-06T11:03:34.807+01:00 level=DEBUG source=runner.go:328 msg="unable to refresh all GPUs with existing runners, performing bootstrap discovery" time=2026-02-06T11:03:34.808+01:00 level=INFO source=server.go:430 msg="starting runner" cmd="C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 56820" time=2026-02-06T11:03:34.808+01:00 level=DEBUG source=server.go:431 msg=subprocess OLLAMA_MODELS=C:\Ollama\models PATH="C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\java8path;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\javapath;C:\\Program Files\\Microsoft SDKs\\Azure\\CLI2\\wbin;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\Program Files\\NVIDIA Corporation\\NVIDIA app\\NvDLISR;C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common;C:\\Program Files\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\170\\Tools\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\160\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\160\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\160\\DTS\\Binn\\;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Local\\nvm\\Current\\nodejs;C:\\Program Files\\Certbot\\bin;C:\\Program Files\\FirefoxPWA\\;C:\\Program Files\\Microsoft SQL Server\\170\\Tools\\Binn\\;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\Program Files (x86)\\Microsoft SQL Server\\170\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\180\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\170\\DTS\\Binn\\;C:\\Program Files\\Go\\bin;C:\\Program Files\\cursor\\resources\\app\\bin;C:\\Program Files\\Git\\cmd;C:\\Program Files\\dotnet\\;C:\\Users\\user\\AppData\\Local\\Programs\\Python\\Python310\\Scripts\\;C:\\Users\\user\\AppData\\Local\\Programs\\Python\\Python310\\;C:\\Users\\user\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\user\\.dotnet\\tools;C:\\Users\\user\\AppData\\Local\\Programs\\Microsoft VS Code\\bin;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Roaming\\npm;C:\\Users\\user\\.lmstudio\\bin;C:\\Users\\user\\AppData\\Local\\Programs\\Ollama;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Local\\nvm\\Current\\nodejs;C:\\Program Files\\OpenSSL-Win64\\bin\\;G:\\Work\\Tools\\GitClean;C:\\Users\\user\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\user\\AppData\\Local\\Programs\\Antigravity\\bin;C:\\Users\\user\\go\\bin;C:\\Users\\user\\.dotnet\\tools" OLLAMA_NEW_ESTIMATES=1 OLLAMA_FLASH_ATTENTION=1 OLLAMA_HOST=0.0.0.0 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_NEW_ENGINE=1 OLLAMA_DEBUG=1 OLLAMA_NUM_PARALLEL=2 OLLAMA_LIBRARY_PATH=C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13 time=2026-02-06T11:03:35.007+01:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=199.8032ms 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=2026-02-06T11:03:35.007+01:00 level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=200.3105ms time=2026-02-06T11:03:35.007+01:00 level=INFO source=cpu_windows.go:148 msg=packages count=1 time=2026-02-06T11:03:35.007+01:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1 time=2026-02-06T11:03:35.007+01:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=20 efficiency=12 threads=20 time=2026-02-06T11:03:35.007+01:00 level=DEBUG source=sched.go:195 msg="updating default concurrency" OLLAMA_MAX_LOADED_MODELS=3 gpu_count=1 time=2026-02-06T11:03:35.010+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=general.alignment default=32 time=2026-02-06T11:03:35.011+01:00 level=DEBUG source=sched.go:231 msg="loading first model" model=C:\Ollama\models\blobs\sha256-65493e1f85b9ea4ba3ed793515fde13cbdbea7d74ad2c662b566b146eab0081e time=2026-02-06T11:03:35.026+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=general.alignment default=32 time=2026-02-06T11:03:35.026+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=glmocr.pooling_type default=0 time=2026-02-06T11:03:35.026+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=false time=2026-02-06T11:03:35.026+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0 time=2026-02-06T11:03:35.026+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=glmocr.rope.dimension_count default=128 time=2026-02-06T11:03:35.026+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=glmocr.vision.num_channels default=3 time=2026-02-06T11:03:35.026+01:00 level=INFO source=server.go:246 msg="enabling flash attention" time=2026-02-06T11:03:35.027+01:00 level=INFO source=server.go:430 msg="starting runner" cmd="C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model C:\\Ollama\\models\\blobs\\sha256-65493e1f85b9ea4ba3ed793515fde13cbdbea7d74ad2c662b566b146eab0081e --port 56827" time=2026-02-06T11:03:35.027+01:00 level=DEBUG source=server.go:431 msg=subprocess OLLAMA_MODELS=C:\Ollama\models PATH="C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\user\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\java8path;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\javapath;C:\\Program Files\\Microsoft SDKs\\Azure\\CLI2\\wbin;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\Program Files\\NVIDIA Corporation\\NVIDIA app\\NvDLISR;C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common;C:\\Program Files\\Microsoft SQL Server\\150\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\170\\Tools\\Binn\\;C:\\Program Files (x86)\\Microsoft SQL Server\\160\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\160\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\160\\DTS\\Binn\\;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Local\\nvm\\Current\\nodejs;C:\\Program Files\\Certbot\\bin;C:\\Program Files\\FirefoxPWA\\;C:\\Program Files\\Microsoft SQL Server\\170\\Tools\\Binn\\;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\Program Files (x86)\\Microsoft SQL Server\\170\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\180\\Tools\\Binn\\;C:\\Program Files\\Microsoft SQL Server\\170\\DTS\\Binn\\;C:\\Program Files\\Go\\bin;C:\\Program Files\\cursor\\resources\\app\\bin;C:\\Program Files\\Git\\cmd;C:\\Program Files\\dotnet\\;C:\\Users\\user\\AppData\\Local\\Programs\\Python\\Python310\\Scripts\\;C:\\Users\\user\\AppData\\Local\\Programs\\Python\\Python310\\;C:\\Users\\user\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\user\\.dotnet\\tools;C:\\Users\\user\\AppData\\Local\\Programs\\Microsoft VS Code\\bin;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Roaming\\npm;C:\\Users\\user\\.lmstudio\\bin;C:\\Users\\user\\AppData\\Local\\Programs\\Ollama;C:\\Users\\user\\AppData\\Local\\nvm;C:\\Users\\user\\AppData\\Local\\nvm\\Current\\nodejs;C:\\Program Files\\OpenSSL-Win64\\bin\\;G:\\Work\\Tools\\GitClean;C:\\Users\\user\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\user\\AppData\\Local\\Programs\\Antigravity\\bin;C:\\Users\\user\\go\\bin;C:\\Users\\user\\.dotnet\\tools" OLLAMA_NEW_ESTIMATES=1 OLLAMA_FLASH_ATTENTION=1 OLLAMA_HOST=0.0.0.0 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_NEW_ENGINE=1 OLLAMA_DEBUG=1 OLLAMA_NUM_PARALLEL=2 OLLAMA_LIBRARY_PATH=C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13 time=2026-02-06T11:03:35.030+01:00 level=INFO source=sched.go:463 msg="system memory" total="63.3 GiB" free="39.5 GiB" free_swap="72.5 GiB" time=2026-02-06T11:03:35.030+01:00 level=INFO source=sched.go:470 msg="gpu memory" id=GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa library=CUDA available="93.7 GiB" free="94.2 GiB" minimum="457.0 MiB" overhead="0 B" time=2026-02-06T11:03:35.030+01:00 level=INFO source=server.go:756 msg="loading model" "model layers"=17 requested=-1 time=2026-02-06T11:03:35.081+01:00 level=INFO source=runner.go:1410 msg="starting ollama engine" time=2026-02-06T11:03:35.083+01:00 level=INFO source=runner.go:1445 msg="Server listening on 127.0.0.1:56827" time=2026-02-06T11:03:35.084+01:00 level=INFO source=runner.go:1283 msg=load request="{Operation:fit LoraPath:[] Parallel:2 BatchSize:512 FlashAttention:Enabled KvSize:8192 KvCacheType: NumThreads:8 GPULayers:17[ID:GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa Layers:17(0..16)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-02-06T11:03:35.092+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=general.alignment default=32 time=2026-02-06T11:03:35.092+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=general.name default="" time=2026-02-06T11:03:35.092+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=general.description default="" time=2026-02-06T11:03:35.092+01:00 level=INFO source=ggml.go:136 msg="" architecture=glmocr file_type=F16 name="" description="" num_tensors=527 num_key_values=47 time=2026-02-06T11:03:35.092+01:00 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-alderlake.dll time=2026-02-06T11:03:35.102+01:00 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: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition, compute capability 12.0, VMM: yes, ID: GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa load_backend: loaded CUDA backend from C:\Users\user\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13\ggml-cuda.dll time=2026-02-06T11:03:35.194+01:00 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=2026-02-06T11:03:35.196+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=glmocr.pooling_type default=0 time=2026-02-06T11:03:35.196+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=false time=2026-02-06T11:03:35.196+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0 time=2026-02-06T11:03:35.196+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=glmocr.rope.dimension_count default=128 time=2026-02-06T11:03:35.196+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=glmocr.vision.num_channels default=3 time=2026-02-06T11:03:43.047+01:00 level=DEBUG source=ggml.go:852 msg="compute graph" nodes=940 splits=1 time=2026-02-06T11:03:47.860+01:00 level=DEBUG source=ggml.go:852 msg="compute graph" nodes=586 splits=2 time=2026-02-06T11:03:54.233+01:00 level=DEBUG source=ggml.go:852 msg="compute graph" nodes=584 splits=2 time=2026-02-06T11:03:54.233+01:00 level=DEBUG source=device.go:240 msg="model weights" device=CUDA0 size="1.9 GiB" time=2026-02-06T11:03:54.233+01:00 level=DEBUG source=device.go:245 msg="model weights" device=CPU size="174.0 MiB" time=2026-02-06T11:03:54.233+01:00 level=DEBUG source=device.go:251 msg="kv cache" device=CUDA0 size="512.0 MiB" time=2026-02-06T11:03:54.233+01:00 level=DEBUG source=device.go:262 msg="compute graph" device=CUDA0 size="1.4 GiB" time=2026-02-06T11:03:54.233+01:00 level=DEBUG source=device.go:267 msg="compute graph" device=CPU size="31.2 MiB" time=2026-02-06T11:03:54.233+01:00 level=DEBUG source=device.go:272 msg="total memory" size="3.9 GiB" time=2026-02-06T11:03:54.233+01:00 level=DEBUG source=server.go:781 msg=memory success=true required.InputWeights=182452224 required.CPU.Graph=32741376 required.CUDA0.ID=GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa required.CUDA0.Weights="[61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 1051455488]" required.CUDA0.Cache="[33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 0]" required.CUDA0.Graph=1455846912 time=2026-02-06T11:03:54.233+01:00 level=DEBUG source=server.go:975 msg="available gpu" id=GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa library=CUDA "available layer vram"="92.3 GiB" backoff=0.00 minimum="457.0 MiB" overhead="0 B" graph="1.4 GiB" time=2026-02-06T11:03:54.233+01:00 level=DEBUG source=server.go:792 msg="new layout created" layers="17[ID:GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa Layers:17(0..16)]" time=2026-02-06T11:03:54.233+01:00 level=INFO source=runner.go:1283 msg=load request="{Operation:alloc LoraPath:[] Parallel:2 BatchSize:512 FlashAttention:Enabled KvSize:8192 KvCacheType: NumThreads:8 GPULayers:17[ID:GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa Layers:17(0..16)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-02-06T11:03:54.240+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=general.alignment default=32 time=2026-02-06T11:03:54.243+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=glmocr.pooling_type default=0 time=2026-02-06T11:03:54.243+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=false time=2026-02-06T11:03:54.243+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0 time=2026-02-06T11:03:54.243+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=glmocr.rope.dimension_count default=128 time=2026-02-06T11:03:54.243+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=glmocr.vision.num_channels default=3 time=2026-02-06T11:03:54.529+01:00 level=DEBUG source=ggml.go:852 msg="compute graph" nodes=940 splits=1 time=2026-02-06T11:03:54.651+01:00 level=DEBUG source=ggml.go:852 msg="compute graph" nodes=586 splits=2 time=2026-02-06T11:03:54.661+01:00 level=DEBUG source=ggml.go:852 msg="compute graph" nodes=584 splits=2 time=2026-02-06T11:03:54.661+01:00 level=DEBUG source=device.go:240 msg="model weights" device=CUDA0 size="1.9 GiB" time=2026-02-06T11:03:54.661+01:00 level=DEBUG source=device.go:245 msg="model weights" device=CPU size="174.0 MiB" time=2026-02-06T11:03:54.661+01:00 level=DEBUG source=device.go:251 msg="kv cache" device=CUDA0 size="512.0 MiB" time=2026-02-06T11:03:54.661+01:00 level=DEBUG source=device.go:262 msg="compute graph" device=CUDA0 size="1.4 GiB" time=2026-02-06T11:03:54.661+01:00 level=DEBUG source=device.go:267 msg="compute graph" device=CPU size="31.2 MiB" time=2026-02-06T11:03:54.661+01:00 level=DEBUG source=device.go:272 msg="total memory" size="3.9 GiB" time=2026-02-06T11:03:54.661+01:00 level=DEBUG source=server.go:781 msg=memory success=true required.InputWeights=182452224 required.CPU.Graph=32741376 required.CUDA0.ID=GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa required.CUDA0.Weights="[61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 61366272 1051455488]" required.CUDA0.Cache="[33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 33554432 0]" required.CUDA0.Graph=1455846912 time=2026-02-06T11:03:54.661+01:00 level=DEBUG source=server.go:975 msg="available gpu" id=GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa library=CUDA "available layer vram"="92.3 GiB" backoff=0.00 minimum="457.0 MiB" overhead="0 B" graph="1.4 GiB" time=2026-02-06T11:03:54.661+01:00 level=DEBUG source=server.go:792 msg="new layout created" layers="17[ID:GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa Layers:17(0..16)]" time=2026-02-06T11:03:54.661+01:00 level=INFO source=runner.go:1283 msg=load request="{Operation:commit LoraPath:[] Parallel:2 BatchSize:512 FlashAttention:Enabled KvSize:8192 KvCacheType: NumThreads:8 GPULayers:17[ID:GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa Layers:17(0..16)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-02-06T11:03:54.661+01:00 level=INFO source=ggml.go:482 msg="offloading 16 repeating layers to GPU" time=2026-02-06T11:03:54.661+01:00 level=INFO source=ggml.go:489 msg="offloading output layer to GPU" time=2026-02-06T11:03:54.661+01:00 level=INFO source=ggml.go:494 msg="offloaded 17/17 layers to GPU" time=2026-02-06T11:03:54.661+01:00 level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="1.9 GiB" time=2026-02-06T11:03:54.661+01:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="174.0 MiB" time=2026-02-06T11:03:54.661+01:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="512.0 MiB" time=2026-02-06T11:03:54.661+01:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="1.4 GiB" time=2026-02-06T11:03:54.661+01:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="31.2 MiB" time=2026-02-06T11:03:54.661+01:00 level=INFO source=device.go:272 msg="total memory" size="3.9 GiB" time=2026-02-06T11:03:54.661+01:00 level=INFO source=sched.go:537 msg="loaded runners" count=1 time=2026-02-06T11:03:54.661+01:00 level=INFO source=server.go:1349 msg="waiting for llama runner to start responding" time=2026-02-06T11:03:54.661+01:00 level=INFO source=server.go:1383 msg="waiting for server to become available" status="llm server loading model" time=2026-02-06T11:03:54.912+01:00 level=DEBUG source=server.go:1393 msg="model load progress 0.13" time=2026-02-06T11:03:55.162+01:00 level=DEBUG source=server.go:1393 msg="model load progress 0.27" time=2026-02-06T11:03:55.412+01:00 level=DEBUG source=server.go:1393 msg="model load progress 0.43" time=2026-02-06T11:03:55.663+01:00 level=DEBUG source=server.go:1393 msg="model load progress 0.64" time=2026-02-06T11:03:55.913+01:00 level=DEBUG source=server.go:1393 msg="model load progress 0.78" time=2026-02-06T11:03:56.163+01:00 level=DEBUG source=server.go:1393 msg="model load progress 0.92" time=2026-02-06T11:03:56.389+01:00 level=DEBUG source=ggml.go:300 msg="key with type not found" key=glmocr.pooling_type default=0 time=2026-02-06T11:03:56.414+01:00 level=INFO source=server.go:1387 msg="llama runner started in 21.38 seconds" time=2026-02-06T11:03:56.414+01:00 level=DEBUG source=sched.go:549 msg="finished setting up" runner.name=registry.ollama.ai/library/glm-ocr:latest runner.inference="[{ID:GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa Library:CUDA}]" runner.size="3.9 GiB" runner.vram="3.9 GiB" runner.parallel=2 runner.pid=2148 runner.model=C:\Ollama\models\blobs\sha256-65493e1f85b9ea4ba3ed793515fde13cbdbea7d74ad2c662b566b146eab0081e runner.num_ctx=4096 time=2026-02-06T11:03:56.422+01:00 level=DEBUG source=server.go:1535 msg="completion request" images=1 prompt=45 format="" time=2026-02-06T11:03:56.524+01:00 level=DEBUG source=cache.go:151 msg="loading cache slot" id=0 cache=0 prompt=1102 used=0 remaining=1102 time=2026-02-06T11:04:04.085+01:00 level=DEBUG source=server.go:1661 msg="prediction aborted, token repeat limit reached" [GIN] 2026/02/06 - 11:04:04 | 200 | 29.3258245s | 127.0.0.1 | POST "/api/chat" time=2026-02-06T11:04:04.085+01:00 level=DEBUG source=sched.go:557 msg="context for request finished" time=2026-02-06T11:04:04.085+01:00 level=DEBUG source=sched.go:310 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/glm-ocr:latest runner.inference="[{ID:GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa Library:CUDA}]" runner.size="3.9 GiB" runner.vram="3.9 GiB" runner.parallel=2 runner.pid=2148 runner.model=C:\Ollama\models\blobs\sha256-65493e1f85b9ea4ba3ed793515fde13cbdbea7d74ad2c662b566b146eab0081e runner.num_ctx=4096 duration=5m0s time=2026-02-06T11:04:04.085+01:00 level=DEBUG source=sched.go:328 msg="after processing request finished event" runner.name=registry.ollama.ai/library/glm-ocr:latest runner.inference="[{ID:GPU-6d0fa353-1e34-e1a4-4bc6-83ff039685fa Library:CUDA}]" runner.size="3.9 GiB" runner.vram="3.9 GiB" runner.parallel=2 runner.pid=2148 runner.model=C:\Ollama\models\blobs\sha256-65493e1f85b9ea4ba3ed793515fde13cbdbea7d74ad2c662b566b146eab0081e runner.num_ctx=4096 refCount=0 [GIN] 2026/02/06 - 11:04:04 | 200 | 5.8562ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/06 - 11:04:13 | 200 | 354.2µs | ::1 | GET "/api/ps" ``` ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.15.5

GiteaMirror added the bug label 2026-04-29 09:38:37 -05:00

GiteaMirror commented 2026-04-29 09:38:39 -05:00

Author

Owner

Copy Link

@rick-github commented on GitHub (Feb 6, 2026):

The ollama server has code that tries to detect when a model has lost coherence and is stuck in a loop. It does this by checking for repeated tokens in the output:

42e1d49fbe/llm/server.go (L1660-L1664)

Unfortunately it looks like the long string of periods in the last line is triggering this code:

To jest (elegancki) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 

<!-- gh-comment-id:3859574768 --> @rick-github commented on GitHub (Feb 6, 2026): The ollama server has code that tries to detect when a model has lost coherence and is stuck in a loop. It does this by checking for repeated tokens in the output: https://github.com/ollama/ollama/blob/42e1d49fbe5683740680be657306dcf66fa2d76d/llm/server.go#L1660-L1664 Unfortunately it looks like the long string of periods in the last line is triggering this code: ``` To jest (elegancki) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ```

GiteaMirror commented 2026-04-29 09:38:40 -05:00

Author

Owner

Copy Link

@illusdolphin commented on GitHub (Feb 6, 2026):

Assuming this needs to be configurable/controllable. Using "....." is a kind of often trick in books (some can build tables based on dots).

<!-- gh-comment-id:3859676591 --> @illusdolphin commented on GitHub (Feb 6, 2026): Assuming this needs to be configurable/controllable. Using "....." is a kind of often trick in books (some can build tables based on dots).

GiteaMirror commented 2026-04-29 09:38:40 -05:00

Author

Owner

Copy Link

@ManManavadaria commented on GitHub (Feb 6, 2026):

Same observation as @rick-github, I was checking the same thing, and it looks like the condition meant to prevent the model’s response from getting stuck in a loop is being triggered because the tokens are identical. In this case, the model’s response is actually correct. There should be a logic to differentiate between a genuinely stuck response and a correct response that happens to contain duplicate tokens

<!-- gh-comment-id:3859701692 --> @ManManavadaria commented on GitHub (Feb 6, 2026): Same observation as @rick-github, I was checking the same thing, and it looks like the condition meant to prevent the model’s response from getting stuck in a loop is being triggered because the tokens are identical. In this case, the model’s response is actually correct. There should be a logic to differentiate between a genuinely stuck response and a correct response that happens to contain duplicate tokens

GiteaMirror commented 2026-04-29 09:38:41 -05:00

Author

Owner

Copy Link

@rick-github commented on GitHub (Feb 6, 2026):

I'm working up a patch to make this configurable and fix the incorrect "done" response (which has been noticed before, #7547). But this should probably be replaced with a more accurate method of determining a looping model.

<!-- gh-comment-id:3859744920 --> @rick-github commented on GitHub (Feb 6, 2026): I'm working up a patch to make this configurable and fix the incorrect `"done"` response (which has been noticed before, #7547). But this should probably be replaced with a more accurate method of determining a looping model.

GiteaMirror commented 2026-04-29 09:38:42 -05:00

Author

Owner

Copy Link

@illusdolphin commented on GitHub (Feb 6, 2026):

It's hard to find "right" value. Models can generate with ~50-200 tokens\s, so if we extend to 300 tokens, it will be just max a few seconds in a loop (that is rare case). Maybe just extend to 300? It should solve most cases with books

<!-- gh-comment-id:3861586813 --> @illusdolphin commented on GitHub (Feb 6, 2026): It's hard to find "right" value. Models can generate with ~50-200 tokens\s, so if we extend to 300 tokens, it will be just max a few seconds in a loop (that is rare case). Maybe just extend to 300? It should solve most cases with books

Sign in to join this conversation.

No Branch/Tag Specified

Branches Tags

main

dhiltgen/ci

parth-launch-plan-gating

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

v0.23.1

v0.23.1-rc0

v0.23.0

v0.23.0-rc0

v0.22.1

v0.22.1-rc1

v0.22.1-rc0

v0.22.0

v0.22.0-rc1

v0.21.3-rc0

v0.21.2-rc1

v0.21.2

v0.21.2-rc0

v0.21.1

v0.21.1-rc1

v0.21.1-rc0

v0.21.0

v0.21.0-rc1

v0.21.0-rc0

v0.20.8-rc0

v0.20.7

v0.20.7-rc1

v0.20.7-rc0

v0.20.6

v0.20.6-rc1

v0.20.6-rc0

v0.20.5

v0.20.5-rc2

v0.20.5-rc1

v0.20.5-rc0

v0.20.4

v0.20.4-rc2

v0.20.4-rc1

v0.20.4-rc0

v0.20.3

v0.20.3-rc0

v0.20.2

v0.20.1

v0.20.1-rc2

v0.20.1-rc1

v0.20.1-rc0

v0.20.0

v0.20.0-rc1

v0.20.0-rc0

v0.19.0

v0.19.0-rc2

v0.19.0-rc1

v0.19.0-rc0

v0.18.4-rc1

v0.18.4-rc0

v0.18.3

v0.18.3-rc2

v0.18.3-rc1

v0.18.3-rc0

v0.18.2

v0.18.2-rc1

v0.18.2-rc0

v0.18.1

v0.18.1-rc1

v0.18.1-rc0

v0.18.0

v0.18.0-rc2

v0.18.0-rc1

v0.18.0-rc0

v0.17.8-rc4

v0.17.8-rc3

v0.17.8-rc2

v0.17.8-rc1

v0.17.8-rc0

v0.17.7

v0.17.7-rc2

v0.17.7-rc1

v0.17.7-rc0

v0.17.6

v0.17.5

v0.17.4

v0.17.3

v0.17.2

v0.17.1

v0.17.1-rc2

v0.17.1-rc1

v0.17.1-rc0

v0.17.0

v0.17.0-rc2

v0.17.0-rc1

v0.17.0-rc0

v0.16.3

v0.16.3-rc2

v0.16.3-rc1

v0.16.3-rc0

v0.16.2

v0.16.2-rc0

v0.16.1

v0.16.0

v0.16.0-rc2

v0.16.0-rc0

v0.16.0-rc1

v0.15.6

v0.15.5

v0.15.5-rc5

v0.15.5-rc4

v0.15.5-rc3

v0.15.5-rc2

v0.15.5-rc1

v0.15.5-rc0

v0.15.4

v0.15.3

v0.15.2

v0.15.1

v0.15.1-rc1

v0.15.1-rc0

v0.15.0-rc6

v0.15.0

v0.15.0-rc5

v0.15.0-rc4

v0.15.0-rc3

v0.15.0-rc2

v0.15.0-rc1

v0.15.0-rc0

v0.14.3

v0.14.3-rc3

v0.14.3-rc2

v0.14.3-rc1

v0.14.3-rc0

v0.14.2

v0.14.2-rc1

v0.14.2-rc0

v0.14.1

v0.14.0-rc11

v0.14.0

v0.14.0-rc10

v0.14.0-rc9

v0.14.0-rc8

v0.14.0-rc7

v0.14.0-rc6

v0.14.0-rc5

v0.14.0-rc4

v0.14.0-rc3

v0.14.0-rc2

v0.14.0-rc1

v0.14.0-rc0

v0.13.5

v0.13.5-rc1

v0.13.5-rc0

v0.13.4-rc2

v0.13.4

v0.13.4-rc1

v0.13.4-rc0

v0.13.3

v0.13.3-rc1

v0.13.3-rc0

v0.13.2

v0.13.2-rc2

v0.13.2-rc1

v0.13.2-rc0

v0.13.1

v0.13.1-rc2

v0.13.1-rc1

v0.13.1-rc0

v0.13.0

v0.13.0-rc0

v0.12.11

v0.12.11-rc1

v0.12.11-rc0

v0.12.10

v0.12.10-rc1

v0.12.10-rc0

v0.12.9-rc0

v0.12.9

v0.12.8

v0.12.8-rc0

v0.12.7

v0.12.7-rc1

v0.12.7-rc0

v0.12.7-citest0

v0.12.6

v0.12.6-rc1

v0.12.6-rc0

v0.12.5

v0.12.5-rc0

v0.12.4

v0.12.4-rc7

v0.12.4-rc6

v0.12.4-rc5

v0.12.4-rc4

v0.12.4-rc3

v0.12.4-rc2

v0.12.4-rc1

v0.12.4-rc0

v0.12.3

v0.12.2

v0.12.2-rc0

v0.12.1

v0.12.1-rc1

v0.12.1-rc2

v0.12.1-rc0

v0.12.0

v0.12.0-rc1

v0.12.0-rc0

v0.11.11

v0.11.11-rc3

v0.11.11-rc2

v0.11.11-rc1

v0.11.11-rc0

v0.11.10

v0.11.9

v0.11.9-rc0

v0.11.8

v0.11.8-rc0

v0.11.7-rc1

v0.11.7-rc0

v0.11.7

v0.11.6

v0.11.6-rc0

v0.11.5-rc4

v0.11.5-rc3

v0.11.5

v0.11.5-rc5

v0.11.5-rc2

v0.11.5-rc1

v0.11.5-rc0

v0.11.4

v0.11.4-rc0

v0.11.3

v0.11.3-rc0

v0.11.2

v0.11.1

v0.11.0-rc0

v0.11.0-rc1

v0.11.0-rc2

v0.11.0

v0.10.2-int1

v0.10.1

v0.10.0

v0.10.0-rc4

v0.10.0-rc3

v0.10.0-rc2

v0.10.0-rc1

v0.10.0-rc0

v0.9.7-rc1

v0.9.7-rc0

v0.9.6

v0.9.6-rc0

v0.9.6-ci0

v0.9.5

v0.9.4-rc5

v0.9.4-rc6

v0.9.4

v0.9.4-rc3

v0.9.4-rc4

v0.9.4-rc1

v0.9.4-rc2

v0.9.4-rc0

v0.9.3

v0.9.3-rc5

v0.9.4-citest0

v0.9.3-rc4

v0.9.3-rc3

v0.9.3-rc2

v0.9.3-rc1

v0.9.3-rc0

v0.9.2

v0.9.1

v0.9.1-rc1

v0.9.1-rc0

v0.9.1-ci1

v0.9.1-ci0

v0.9.0

v0.9.0-rc0

v0.8.0

v0.8.0-rc0

v0.7.1-rc2

v0.7.1

v0.7.1-rc1

v0.7.1-rc0

v0.7.0

v0.7.0-rc1

v0.7.0-rc0

v0.6.9-rc0

v0.6.8

v0.6.8-rc0

v0.6.7

v0.6.7-rc2

v0.6.7-rc1

v0.6.7-rc0

v0.6.6

v0.6.6-rc2

v0.6.6-rc1

v0.6.6-rc0

v0.6.5-rc1

v0.6.5

v0.6.5-rc0

v0.6.4-rc0

v0.6.4

v0.6.3-rc1

v0.6.3

v0.6.3-rc0

v0.6.2

v0.6.2-rc0

v0.6.1

v0.6.1-rc0

v0.6.0-rc0

v0.6.0

v0.5.14-rc0

v0.5.13

v0.5.13-rc6

v0.5.13-rc5

v0.5.13-rc4

v0.5.13-rc3

v0.5.13-rc2

v0.5.13-rc1

v0.5.13-rc0

v0.5.12

v0.5.12-rc1

v0.5.12-rc0

v0.5.11

v0.5.10

v0.5.9

v0.5.9-rc0

v0.5.8-rc13

v0.5.8

v0.5.8-rc12

v0.5.8-rc11

v0.5.8-rc10

v0.5.8-rc9

v0.5.8-rc8

v0.5.8-rc7

v0.5.8-rc6

v0.5.8-rc5

v0.5.8-rc4

v0.5.8-rc3

v0.5.8-rc2

v0.5.8-rc1

v0.5.8-rc0

v0.5.7

v0.5.6

v0.5.5

v0.5.5-rc0

v0.5.4

v0.5.3

v0.5.3-rc0

v0.5.2

v0.5.2-rc3

v0.5.2-rc2

v0.5.2-rc1

v0.5.2-rc0

v0.5.1

v0.5.0

v0.5.0-rc1

v0.4.8-rc0

v0.4.7

v0.4.6

v0.4.5

v0.4.4

v0.4.3

v0.4.3-rc0

v0.4.2

v0.4.2-rc1

v0.4.2-rc0

v0.4.1

v0.4.1-rc0

v0.4.0

v0.4.0-rc8

v0.4.0-rc7

v0.4.0-rc6

v0.4.0-rc5

v0.4.0-rc4

v0.4.0-rc3

v0.4.0-rc2

v0.4.0-rc1

v0.4.0-rc0

v0.4.0-ci3

v0.3.14

v0.3.14-rc0

v0.3.13

v0.3.12

v0.3.12-rc5

v0.3.12-rc4

v0.3.12-rc3

v0.3.12-rc2

v0.3.12-rc1

v0.3.11

v0.3.11-rc4

v0.3.11-rc3

v0.3.11-rc2

v0.3.11-rc1

v0.3.10

v0.3.10-rc1

v0.3.9

v0.3.8

v0.3.7

v0.3.7-rc6

v0.3.7-rc5

v0.3.7-rc4

v0.3.7-rc3

v0.3.7-rc2

v0.3.7-rc1

v0.3.6

v0.3.5

v0.3.4

v0.3.3

v0.3.2

v0.3.1

v0.3.0

v0.2.8

v0.2.8-rc2

v0.2.8-rc1

v0.2.7

v0.2.6

v0.2.5

v0.2.4

v0.2.3

v0.2.2

v0.2.2-rc2

v0.2.2-rc1

v0.2.1

v0.2.0

v0.1.49-rc14

v0.1.49-rc13

v0.1.49-rc12

v0.1.49-rc11

v0.1.49-rc10

v0.1.49-rc9

v0.1.49-rc8

v0.1.49-rc7

v0.1.49-rc6

v0.1.49-rc4

v0.1.49-rc5

v0.1.49-rc3

v0.1.49-rc2

v0.1.49-rc1

v0.1.48

v0.1.47

v0.1.46

v0.1.45-rc5

v0.1.45

v0.1.45-rc4

v0.1.45-rc3

v0.1.45-rc2

v0.1.45-rc1

v0.1.44

v0.1.43

v0.1.42

v0.1.41

v0.1.40

v0.1.40-rc1

v0.1.39

v0.1.39-rc2

v0.1.39-rc1

v0.1.38

v0.1.37

v0.1.36

v0.1.35

v0.1.35-rc1

v0.1.34

v0.1.34-rc1

v0.1.33

v0.1.33-rc7

v0.1.33-rc6

v0.1.33-rc5

v0.1.33-rc4

v0.1.33-rc3

v0.1.33-rc2

v0.1.33-rc1

v0.1.32

v0.1.32-rc2

v0.1.32-rc1

v0.1.31

v0.1.30

v0.1.29

v0.1.28

v0.1.27

v0.1.26

v0.1.25

v0.1.24

v0.1.23

v0.1.22

v0.1.21

v0.1.20

v0.1.19

v0.1.18

v0.1.17

v0.1.16

v0.1.15

v0.1.14

v0.1.13

v0.1.12

v0.1.11

v0.1.10

v0.1.9

v0.1.8

v0.1.7

v0.1.6

v0.1.5

v0.1.4

v0.1.3

v0.1.2

v0.1.1

v0.1.0

v0.0.21

v0.0.20

v0.0.19

v0.0.18

v0.0.17

v0.0.16

v0.0.15

v0.0.14

v0.0.13

v0.0.12

v0.0.11

v0.0.10

v0.0.9

v0.0.8

v0.0.7

v0.0.6

v0.0.5

v0.0.4

v0.0.3

v0.0.2

v0.0.1

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

Milestone

No items

No Milestone

Projects

Clear projects

No project

Assignees

Clear assignees

GiteaMirror ninjasurge

No Assignees

1 Participants

Notifications

Subscribe

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/ollama#55723