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

[GH-ISSUE #11416] Qwen2.5vl on ubuntu version qwen2.5vl:7b and version qwen2.5vl:3b do not work! But version qwen2.5vl:32b works fine. #7535

New Issue
Closed
opened 2026-04-12 19:38:06 -05:00 by GiteaMirror · 7 comments
GiteaMirror commented 2026-04-12 19:38:06 -05:00
Owner
Copy Link

Originally created by @DewiarQR on GitHub (Jul 14, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11416

What is the issue?

qwen2.5vl on ubuntu version qwen2.5vl:7b and version qwen2.5vl:3b do not work! But version qwen2.5vl:32b works fine. I checked on two different servers with ubuntu, and it is the same there and there. Smaller models give this:
kk ... !¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!s¡!¡ !¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡ !!!!!!!!To!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! !¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡! !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!To!! ¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡ !¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!k¡!¡!k¡!¡!¡!¡!¡!¡!kk¡!¡ !к¡!¡!к¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡! ¡! ... !к¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!kk¡!k¡!¡!k¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!k¡!¡!¡!¡!k¡!¡!¡!¡!k¡!¡!¡!¡!k¡!¡!kkkk¡ !To!!!!!!!!!!!!!!!!!!!! !¡!¡!k¡!¡!¡!k¡!¡!¡!¡!¡!¡!¡!¡!kk¡!¡!¡!¡!¡!¡!¡ !¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡! ¡!¡!¡!k¡!¡!kk¡!¡!¡!¡!¡!¡!k¡!k¡!k¡!¡!¡!¡!¡!k¡ !¡!¡!k¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!k¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!k¡!¡!¡!¡!k¡!¡!¡!k¡!¡! k¡!¡!¡!k¡!¡!k¡!kk¡!k¡!¡!¡!k¡!¡!¡!¡!¡!¡!k¡!¡ !¡!¡!¡!¡!¡!¡!k¡!¡!¡!¡!k¡!¡!¡!¡!¡!k¡!¡!¡!¡!¡! ¡!k¡!¡!¡!¡!¡!k¡!¡!¡!¡!¡!¡!k¡!¡!¡!¡!¡!¡!¡!¡! ¡!kk¡!¡!¡!¡!¡!¡!k¡!k¡!¡!¡!¡!kk¡!k¡!¡!¡!k¡!¡! ¡!¡!¡!¡!¡!к¡!к¡!¡!¡!¡!¡!kkk¡!¡!¡!¡!¡!¡!k¡!k¡!kkk¡!k¡!k¡!k¡!k¡!k¡!k¡!k¡!k¡!k¡!k¡!k¡!k¡!¡!k¡!¡!k¡!¡! !¡!kkk¡!k¡!¡!¡!¡!k¡!k¡!¡!¡!kk¡!k¡!k¡!k¡!k¡!k¡!k¡!kkkk¡!k¡!k¡!kkkk¡!k¡!k¡!kkkk¡!k¡!k¡!¡!k¡!¡!k¡!¡!¡!¡!¡!¡!¡!¡!kkkk¡!k ... ¡!¡!¡!¡!¡!k¡!¡!kkkk¡!¡!k¡¡!¡!¡!¡!¡!k¡!¡!¡!k¡!¡!¡!k¡!¡!¡!¡!k¡!¡!¡!k¡!¡!¡!kkkk¡!¡!k¡!¡!kkkk¡!k¡ !¡!¡!¡!k¡!¡!k¡!¡!¡!¡!¡!¡!¡!k¡!kk¡!¡!¡!¡!¡!¡ !k¡!k¡!k¡!¡!¡!¡!¡!¡!k¡!¡!¡!¡!¡!k¡!¡!¡!¡!k¡!¡ !к¡!¡!¡!к¡!kk¡!¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡! ¡!k¡!¡!¡!kkk¡!kkk¡!¡!kk¡!¡!k¡!k¡!¡!kk!¡!¡!k¡!kkk¡!¡!¡!kkkkkkkk¡!kkk!kkkk¡!k¡!kk!¡!kkk! k¡!kk¡!¡!k¡!¡!kkk¡!¡!¡!¡!k¡!¡!k¡!¡!kkk!¡!kkk!¡!kk¡!kkkkk!k¡!kkk¡!kkk¡!k¡!kkkkkkkkkkkkk k¡!kkkkk¡!kk!kkkkk¡!kkkk!k¡!k¡!kkkkkkk¡!kkkkk!kkkkk!kkk¡!k!¡!kkk!kkkk!k¡!kkk!kkkk!kkkk kk!kkkkk¡!kkk!kkkkkk!k!k!k¡!k¡!k!¡!k¡¡k!¡!!k!¡!¡!!¡!¡!¡!k¡!¡¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡¡! ¡!¡!¡!¡!к¡¡¡!¡!¡!¡!¡!¡!к ... ¡! ... ¡! ... !¡ ... ¡! ... !¡¡¡¡!¡¡¡!¡!¡¡¡¡¡¡¡¡! ...

Relevant log output

OS

Ubuntu 24

GPU

Nvidia 4090, A6000

CPU

No response

Ollama version

0.9.3

Originally created by @DewiarQR on GitHub (Jul 14, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11416 ### What is the issue? qwen2.5vl on ubuntu version qwen2.5vl:7b and version qwen2.5vl:3b do not work! But version qwen2.5vl:32b works fine. I checked on two different servers with ubuntu, and it is the same there and there. Smaller models give this: kk ... !¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!s¡!¡ !¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡ !!!!!!!!To!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! !¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡! !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!To!! ¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡ !¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!k¡!¡!k¡!¡!¡!¡!¡!¡!kk¡!¡ !к¡!¡!к¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡! ¡! ... !к¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!kk¡!k¡!¡!k¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!k¡!¡!¡!¡!k¡!¡!¡!¡!k¡!¡!¡!¡!k¡!¡!kkkk¡ !To!!!!!!!!!!!!!!!!!!!! !¡!¡!k¡!¡!¡!k¡!¡!¡!¡!¡!¡!¡!¡!kk¡!¡!¡!¡!¡!¡!¡ !¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡! ¡!¡!¡!k¡!¡!kk¡!¡!¡!¡!¡!¡!k¡!k¡!k¡!¡!¡!¡!¡!k¡ !¡!¡!k¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!k¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!k¡!¡!¡!¡!k¡!¡!¡!k¡!¡! k¡!¡!¡!k¡!¡!k¡!kk¡!k¡!¡!¡!k¡!¡!¡!¡!¡!¡!k¡!¡ !¡!¡!¡!¡!¡!¡!k¡!¡!¡!¡!k¡!¡!¡!¡!¡!k¡!¡!¡!¡!¡! ¡!k¡!¡!¡!¡!¡!k¡!¡!¡!¡!¡!¡!k¡!¡!¡!¡!¡!¡!¡!¡! ¡!kk¡!¡!¡!¡!¡!¡!k¡!k¡!¡!¡!¡!kk¡!k¡!¡!¡!k¡!¡! ¡!¡!¡!¡!¡!к¡!к¡!¡!¡!¡!¡!kkk¡!¡!¡!¡!¡!¡!k¡!k¡!kkk¡!k¡!k¡!k¡!k¡!k¡!k¡!k¡!k¡!k¡!k¡!k¡!k¡!¡!k¡!¡!k¡!¡! !¡!kkk¡!k¡!¡!¡!¡!k¡!k¡!¡!¡!kk¡!k¡!k¡!k¡!k¡!k¡!k¡!kkkk¡!k¡!k¡!kkkk¡!k¡!k¡!kkkk¡!k¡!k¡!¡!k¡!¡!k¡!¡!¡!¡!¡!¡!¡!¡!kkkk¡!k ... ¡!¡!¡!¡!¡!k¡!¡!kkkk¡!¡!k¡¡!¡!¡!¡!¡!k¡!¡!¡!k¡!¡!¡!k¡!¡!¡!¡!k¡!¡!¡!k¡!¡!¡!kkkk¡!¡!k¡!¡!kkkk¡!k¡ !¡!¡!¡!k¡!¡!k¡!¡!¡!¡!¡!¡!¡!k¡!kk¡!¡!¡!¡!¡!¡ !k¡!k¡!k¡!¡!¡!¡!¡!¡!k¡!¡!¡!¡!¡!k¡!¡!¡!¡!k¡!¡ !к¡!¡!¡!к¡!kk¡!¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡!kk¡! ¡!k¡!¡!¡!kkk¡!kkk¡!¡!kk¡!¡!k¡!k¡!¡!kk!¡!¡!k¡!kkk¡!¡!¡!kkkkkkkk¡!kkk!kkkk¡!k¡!kk!¡!kkk! k¡!kk¡!¡!k¡!¡!kkk¡!¡!¡!¡!k¡!¡!k¡!¡!kkk!¡!kkk!¡!kk¡!kkkkk!k¡!kkk¡!kkk¡!k¡!kkkkkkkkkkkkk k¡!kkkkk¡!kk!kkkkk¡!kkkk!k¡!k¡!kkkkkkk¡!kkkkk!kkkkk!kkk¡!k!¡!kkk!kkkk!k¡!kkk!kkkk!kkkk kk!kkkkk¡!kkk!kkkkkk!k!k!k¡!k¡!k!¡!k¡¡k!¡!!k!¡!¡!!¡!¡!¡!k¡!¡¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡!¡¡! ¡!¡!¡!¡!к¡¡¡!¡!¡!¡!¡!¡!к ... ¡! ... ¡! ... !¡ ... ¡! ... !¡¡¡¡!¡¡¡!¡!¡¡¡¡¡¡¡¡! ... ### Relevant log output ```shell ``` ### OS Ubuntu 24 ### GPU Nvidia 4090, A6000 ### CPU _No response_ ### Ollama version 0.9.3
GiteaMirror added the bug label 2026-04-12 19:38:06 -05:00
GiteaMirror commented 2026-04-12 19:38:07 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 14, 2025):

Where did you get the models from? Server logs may help with debugging.

<!-- gh-comment-id:3069754960 --> @rick-github commented on GitHub (Jul 14, 2025): Where did you get the models from? [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) may help with debugging.
GiteaMirror commented 2026-04-12 19:38:08 -05:00
Author
Owner
Copy Link

@DewiarQR commented on GitHub (Jul 14, 2025):

Откуда вы взяли модели? Логи сервера могут помочь в отладке.

I take it from the official repository https://ollama.com/library/qwen2.5vl

<!-- gh-comment-id:3069797349 --> @DewiarQR commented on GitHub (Jul 14, 2025): > Откуда вы взяли модели? [Логи сервера](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) могут помочь в отладке. I take it from the official repository https://ollama.com/library/qwen2.5vl
GiteaMirror commented 2026-04-12 19:38:09 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 14, 2025):

Server logs may help with debugging.

<!-- gh-comment-id:3069803304 --> @rick-github commented on GitHub (Jul 14, 2025): [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) may help with debugging.
GiteaMirror commented 2026-04-12 19:38:09 -05:00
Author
Owner
Copy Link

@DewiarQR commented on GitHub (Jul 18, 2025):

journalctl -u ollama --no-pager --follow --pager-end
июл 18 21:38:05 dewiar-ai systemd[1]: /etc/systemd/system/ollama.service.d/override.conf:1: Assignment outside of section. Ignoring.
июл 18 21:38:05 dewiar-ai systemd[1]: /etc/systemd/system/ollama.service.d/override.conf:2: Assignment outside of section. Ignoring.
июл 18 21:38:05 dewiar-ai systemd[1]: /etc/systemd/system/ollama.service.d/override.conf:3: Assignment outside of section. Ignoring.
июл 18 21:38:10 dewiar-ai systemd[1]: Started ollama.service - Ollama Service.
июл 18 21:38:10 dewiar-ai ollama[2420]: time=2025-07-18T21:38:10.862+03:00 level=INFO source=routes.go:1235 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:true OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434/ OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE:q4_0 OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:5 OLLAMA_MODELS:/usr/share/ollama/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[* http://localhost/ https://localhost/ http://localhost/:* https://localhost/:* http://127.0.0.1/ https://127.0.0.1/ http://127.0.0.1/:* https://127.0.0.1/:* http://0.0.0.0/ https://0.0.0.0/ http://0.0.0.0/:* https://0.0.0.0/:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
июл 18 21:38:11 dewiar-ai ollama[2420]: time=2025-07-18T21:38:11.041+03:00 level=INFO source=images.go:476 msg="total blobs: 81"
июл 18 21:38:11 dewiar-ai ollama[2420]: time=2025-07-18T21:38:11.043+03:00 level=INFO source=images.go:483 msg="total unused blobs removed: 0"
июл 18 21:38:11 dewiar-ai ollama[2420]: time=2025-07-18T21:38:11.046+03:00 level=INFO source=routes.go:1288 msg="Listening on [::]:11434 (version 0.9.3)"
июл 18 21:38:11 dewiar-ai ollama[2420]: time=2025-07-18T21:38:11.055+03:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
июл 18 21:38:11 dewiar-ai ollama[2420]: time=2025-07-18T21:38:11.868+03:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-e7f8c414-e63e-8fb7-3de3-06dac76a4b04 library=cuda variant=v12 compute=8.6 driver=12.9 name="NVIDIA RTX A6000" total="47.4 GiB" available="47.1 GiB"
июл 18 21:40:13 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:40:13 | 200 | 2.674579ms | 192.168.1.48 | GET "/api/version"
июл 18 21:40:13 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:40:13 | 200 | 754.059µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:40:13 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:40:13 | 200 | 9.587239ms | 192.168.1.48 | GET "/api/tags"
июл 18 21:40:57 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:40:57 | 200 | 82.623µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:40:57 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:40:57 | 200 | 87.023µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:40:57 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:40:57 | 200 | 6.860771ms | 192.168.1.48 | GET "/api/tags"
июл 18 21:40:58 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:40:58 | 200 | 88.211µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:40:58 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:40:58 | 200 | 58.667µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:40:58 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:40:58 | 200 | 3.933283ms | 192.168.1.48 | GET "/api/tags"
июл 18 21:41:16 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:41:16 | 200 | 73.195µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:41:16 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:41:16 | 200 | 125.506µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:41:16 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:41:16 | 200 | 4.416259ms | 192.168.1.48 | GET "/api/tags"
июл 18 21:41:17 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:41:17 | 200 | 98.826µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:41:17 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:41:17 | 200 | 162.452µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:41:17 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:41:17 | 200 | 8.228873ms | 192.168.1.48 | GET "/api/tags"
июл 18 21:41:17 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:41:17 | 200 | 75.36µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:41:17 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:41:17 | 200 | 75.36µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:41:17 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:41:17 | 200 | 6.881757ms | 192.168.1.48 | GET "/api/tags"
июл 18 21:41:25 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:41:25 | 200 | 70.959µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:41:25 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:41:25 | 200 | 70.959µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:41:25 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:41:25 | 200 | 4.107911ms | 192.168.1.48 | GET "/api/tags"
июл 18 21:42:35 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:42:35 | 200 | 73.119µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:42:35 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:42:35 | 200 | 50.91µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:42:35 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:42:35 | 200 | 8.946062ms | 192.168.1.48 | GET "/api/tags"
июл 18 21:42:37 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:42:37 | 200 | 90.158µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:42:37 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:42:37 | 200 | 38.27µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:42:37 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:42:37 | 200 | 6.705531ms | 192.168.1.48 | GET "/api/tags"
июл 18 21:42:37 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:42:37 | 200 | 76.541µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:42:37 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:42:37 | 200 | 50.421µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:42:37 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:42:37 | 200 | 9.612183ms | 192.168.1.48 | GET "/api/tags"
июл 18 21:42:38 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:42:38 | 200 | 99.028µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:42:38 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:42:38 | 200 | 49.304µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:42:38 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:42:38 | 200 | 8.211767ms | 192.168.1.48 | GET "/api/tags"
июл 18 21:42:59 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:42:59 | 200 | 78.079µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:42:59 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:42:59 | 200 | 48.887µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:42:59 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:42:59 | 200 | 6.733129ms | 192.168.1.48 | GET "/api/tags"
июл 18 21:43:28 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:43:28 | 200 | 197.505µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:43:28 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:43:28 | 200 | 49.376µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:43:28 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:43:28 | 200 | 7.471603ms | 192.168.1.48 | GET "/api/tags"
июл 18 21:44:36 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:44:36 | 200 | 117.822µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:44:36 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:44:36 | 200 | 50.076µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:44:36 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:44:36 | 200 | 7.978607ms | 192.168.1.48 | GET "/api/tags"
июл 18 21:45:25 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:45:25 | 200 | 49.588µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:45:25 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:45:25 | 200 | 37.784µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:45:25 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:45:25 | 200 | 5.763366ms | 192.168.1.48 | GET "/api/tags"
июл 18 21:45:51 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:45:51 | 200 | 71.238µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:45:51 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:45:51 | 200 | 87.441µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:45:51 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:45:51 | 200 | 7.298139ms | 192.168.1.48 | GET "/api/tags"
июл 18 21:46:56 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:46:56 | 200 | 108.881µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:46:56 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:46:56 | 200 | 54.475µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:46:56 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:46:56 | 200 | 6.684716ms | 192.168.1.48 | GET "/api/tags"
июл 18 21:47:28 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:47:28 | 200 | 77.244µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:47:28 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:47:28 | 200 | 50.076µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:47:28 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:47:28 | 200 | 8.869283ms | 192.168.1.48 | GET "/api/tags"
июл 18 21:47:29 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:47:29 | 200 | 72.704µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:47:29 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:47:29 | 200 | 77.174µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:47:29 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:47:29 | 200 | 10.302346ms | 192.168.1.48 | GET "/api/tags"
июл 18 21:48:09 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:48:09 | 200 | 87.371µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:48:09 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:48:09 | 200 | 60.203µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:48:09 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:48:09 | 200 | 8.397463ms | 192.168.1.48 | GET "/api/tags"
июл 18 21:48:09 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:48:09 | 200 | 90.584µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:48:09 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:48:09 | 200 | 50.844µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:48:09 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:48:09 | 200 | 6.583135ms | 192.168.1.48 | GET "/api/tags"
июл 18 21:48:10 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:48:10 | 200 | 70.33µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:48:10 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:48:10 | 200 | 70.609µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:48:10 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:48:10 | 200 | 6.514133ms | 192.168.1.48 | GET "/api/tags"
июл 18 21:49:45 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:49:45 | 200 | 86.812µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:49:45 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:49:45 | 200 | 62.438µs | 192.168.1.48 | GET "/api/ps"
июл 18 21:49:45 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:49:45 | 200 | 6.691764ms | 192.168.1.48 | GET "/api/tags"
июл 18 21:50:03 dewiar-ai ollama[2420]: time=2025-07-18T21:50:03.278+03:00 level=INFO source=sched.go:788 msg="new model will fit in available VRAM in single GPU, loading" model=/usr/share/ollama/.ollama/models/blobs/sha256-3839a254cf2d00b208c6e2524c129e4438f9d106bba4c3fbc12b631f519d1de1 gpu=GPU-e7f8c414-e63e-8fb7-3de3-06dac76a4b04 parallel=2 available=49952456704 required="4.1 GiB"
июл 18 21:50:03 dewiar-ai ollama[2420]: time=2025-07-18T21:50:03.457+03:00 level=INFO source=server.go:135 msg="system memory" total="188.6 GiB" free="183.9 GiB" free_swap="8.0 GiB"
июл 18 21:50:03 dewiar-ai ollama[2420]: time=2025-07-18T21:50:03.640+03:00 level=INFO source=server.go:175 msg=offload library=cuda layers.requested=-1 layers.model=31 layers.offload=31 layers.split="" memory.available="[46.5 GiB]" memory.gpu_overhead="0 B" memory.required.full="4.1 GiB" memory.required.partial="4.1 GiB" memory.required.kv="120.0 MiB" memory.required.allocations="[4.1 GiB]" memory.weights.total="1.4 GiB" memory.weights.repeating="1.0 GiB" memory.weights.nonrepeating="420.4 MiB" memory.graph.full="2.0 GiB" memory.graph.partial="3.7 GiB"
июл 18 21:50:03 dewiar-ai ollama[2420]: time=2025-07-18T21:50:03.640+03:00 level=INFO source=server.go:218 msg="enabling flash attention"
июл 18 21:50:03 dewiar-ai ollama[2420]: time=2025-07-18T21:50:03.775+03:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-3839a254cf2d00b208c6e2524c129e4438f9d106bba4c3fbc12b631f519d1de1 --ctx-size 8192 --batch-size 512 --n-gpu-layers 31 --threads 8 --flash-attn --kv-cache-type q4_0 --parallel 2 --port 42047"
июл 18 21:50:03 dewiar-ai ollama[2420]: time=2025-07-18T21:50:03.776+03:00 level=INFO source=sched.go:483 msg="loaded runners" count=1
июл 18 21:50:03 dewiar-ai ollama[2420]: time=2025-07-18T21:50:03.776+03:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding"
июл 18 21:50:03 dewiar-ai ollama[2420]: time=2025-07-18T21:50:03.778+03:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding"
июл 18 21:50:03 dewiar-ai ollama[2420]: time=2025-07-18T21:50:03.796+03:00 level=INFO source=runner.go:925 msg="starting ollama engine"
июл 18 21:50:03 dewiar-ai ollama[2420]: time=2025-07-18T21:50:03.796+03:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:42047"
июл 18 21:50:03 dewiar-ai ollama[2420]: time=2025-07-18T21:50:03.913+03:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3n file_type=Q4_K_M name="" description="" num_tensors=727 num_key_values=40
июл 18 21:50:04 dewiar-ai ollama[2420]: time=2025-07-18T21:50:04.033+03:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model"
июл 18 21:50:04 dewiar-ai ollama[2420]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
июл 18 21:50:04 dewiar-ai ollama[2420]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
июл 18 21:50:04 dewiar-ai ollama[2420]: ggml_cuda_init: found 1 CUDA devices:
июл 18 21:50:04 dewiar-ai ollama[2420]: Device 0: NVIDIA RTX A6000, compute capability 8.6, VMM: yes
июл 18 21:50:04 dewiar-ai ollama[2420]: load_backend: loaded CUDA backend from /usr/local/lib/ollama/libggml-cuda.so
июл 18 21:50:04 dewiar-ai ollama[2420]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-sandybridge.so
июл 18 21:50:04 dewiar-ai ollama[2420]: time=2025-07-18T21:50:04.500+03:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc)
июл 18 21:50:04 dewiar-ai ollama[2420]: time=2025-07-18T21:50:04.640+03:00 level=INFO source=ggml.go:359 msg="model weights" buffer=CUDA0 size="5.2 GiB"
июл 18 21:50:04 dewiar-ai ollama[2420]: time=2025-07-18T21:50:04.641+03:00 level=INFO source=ggml.go:359 msg="model weights" buffer=CPU size="420.4 MiB"
июл 18 21:50:04 dewiar-ai ollama[2420]: time=2025-07-18T21:50:04.658+03:00 level=INFO source=ggml.go:648 msg="compute graph" backend=CUDA0 buffer_type=CUDA0 size="79.0 MiB"
июл 18 21:50:04 dewiar-ai ollama[2420]: time=2025-07-18T21:50:04.658+03:00 level=INFO source=ggml.go:648 msg="compute graph" backend=CPU buffer_type=CPU size="12.5 MiB"
июл 18 21:50:23 dewiar-ai ollama[2420]: time=2025-07-18T21:50:23.385+03:00 level=INFO source=server.go:637 msg="llama runner started in 19.61 seconds"
июл 18 21:50:24 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:50:24 | 200 | 22.239422255s | 192.168.1.48 | POST "/api/chat"
июл 18 21:51:49 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:51:49 | 200 | 359.071409ms | 192.168.1.48 | POST "/api/chat"

<!-- gh-comment-id:3090412250 --> @DewiarQR commented on GitHub (Jul 18, 2025): journalctl -u ollama --no-pager --follow --pager-end июл 18 21:38:05 dewiar-ai systemd[1]: /etc/systemd/system/ollama.service.d/override.conf:1: Assignment outside of section. Ignoring. июл 18 21:38:05 dewiar-ai systemd[1]: /etc/systemd/system/ollama.service.d/override.conf:2: Assignment outside of section. Ignoring. июл 18 21:38:05 dewiar-ai systemd[1]: /etc/systemd/system/ollama.service.d/override.conf:3: Assignment outside of section. Ignoring. июл 18 21:38:10 dewiar-ai systemd[1]: Started ollama.service - Ollama Service. июл 18 21:38:10 dewiar-ai ollama[2420]: time=2025-07-18T21:38:10.862+03:00 level=INFO source=routes.go:1235 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:true OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434/ OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE:q4_0 OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:5 OLLAMA_MODELS:/usr/share/ollama/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[* http://localhost/ https://localhost/ http://localhost/:* https://localhost/:* http://127.0.0.1/ https://127.0.0.1/ http://127.0.0.1/:* https://127.0.0.1/:* http://0.0.0.0/ https://0.0.0.0/ http://0.0.0.0/:* https://0.0.0.0/:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" июл 18 21:38:11 dewiar-ai ollama[2420]: time=2025-07-18T21:38:11.041+03:00 level=INFO source=images.go:476 msg="total blobs: 81" июл 18 21:38:11 dewiar-ai ollama[2420]: time=2025-07-18T21:38:11.043+03:00 level=INFO source=images.go:483 msg="total unused blobs removed: 0" июл 18 21:38:11 dewiar-ai ollama[2420]: time=2025-07-18T21:38:11.046+03:00 level=INFO source=routes.go:1288 msg="Listening on [::]:11434 (version 0.9.3)" июл 18 21:38:11 dewiar-ai ollama[2420]: time=2025-07-18T21:38:11.055+03:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs" июл 18 21:38:11 dewiar-ai ollama[2420]: time=2025-07-18T21:38:11.868+03:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-e7f8c414-e63e-8fb7-3de3-06dac76a4b04 library=cuda variant=v12 compute=8.6 driver=12.9 name="NVIDIA RTX A6000" total="47.4 GiB" available="47.1 GiB" июл 18 21:40:13 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:40:13 | 200 | 2.674579ms | 192.168.1.48 | GET "/api/version" июл 18 21:40:13 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:40:13 | 200 | 754.059µs | 192.168.1.48 | GET "/api/ps" июл 18 21:40:13 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:40:13 | 200 | 9.587239ms | 192.168.1.48 | GET "/api/tags" июл 18 21:40:57 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:40:57 | 200 | 82.623µs | 192.168.1.48 | GET "/api/ps" июл 18 21:40:57 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:40:57 | 200 | 87.023µs | 192.168.1.48 | GET "/api/ps" июл 18 21:40:57 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:40:57 | 200 | 6.860771ms | 192.168.1.48 | GET "/api/tags" июл 18 21:40:58 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:40:58 | 200 | 88.211µs | 192.168.1.48 | GET "/api/ps" июл 18 21:40:58 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:40:58 | 200 | 58.667µs | 192.168.1.48 | GET "/api/ps" июл 18 21:40:58 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:40:58 | 200 | 3.933283ms | 192.168.1.48 | GET "/api/tags" июл 18 21:41:16 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:41:16 | 200 | 73.195µs | 192.168.1.48 | GET "/api/ps" июл 18 21:41:16 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:41:16 | 200 | 125.506µs | 192.168.1.48 | GET "/api/ps" июл 18 21:41:16 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:41:16 | 200 | 4.416259ms | 192.168.1.48 | GET "/api/tags" июл 18 21:41:17 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:41:17 | 200 | 98.826µs | 192.168.1.48 | GET "/api/ps" июл 18 21:41:17 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:41:17 | 200 | 162.452µs | 192.168.1.48 | GET "/api/ps" июл 18 21:41:17 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:41:17 | 200 | 8.228873ms | 192.168.1.48 | GET "/api/tags" июл 18 21:41:17 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:41:17 | 200 | 75.36µs | 192.168.1.48 | GET "/api/ps" июл 18 21:41:17 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:41:17 | 200 | 75.36µs | 192.168.1.48 | GET "/api/ps" июл 18 21:41:17 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:41:17 | 200 | 6.881757ms | 192.168.1.48 | GET "/api/tags" июл 18 21:41:25 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:41:25 | 200 | 70.959µs | 192.168.1.48 | GET "/api/ps" июл 18 21:41:25 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:41:25 | 200 | 70.959µs | 192.168.1.48 | GET "/api/ps" июл 18 21:41:25 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:41:25 | 200 | 4.107911ms | 192.168.1.48 | GET "/api/tags" июл 18 21:42:35 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:42:35 | 200 | 73.119µs | 192.168.1.48 | GET "/api/ps" июл 18 21:42:35 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:42:35 | 200 | 50.91µs | 192.168.1.48 | GET "/api/ps" июл 18 21:42:35 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:42:35 | 200 | 8.946062ms | 192.168.1.48 | GET "/api/tags" июл 18 21:42:37 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:42:37 | 200 | 90.158µs | 192.168.1.48 | GET "/api/ps" июл 18 21:42:37 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:42:37 | 200 | 38.27µs | 192.168.1.48 | GET "/api/ps" июл 18 21:42:37 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:42:37 | 200 | 6.705531ms | 192.168.1.48 | GET "/api/tags" июл 18 21:42:37 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:42:37 | 200 | 76.541µs | 192.168.1.48 | GET "/api/ps" июл 18 21:42:37 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:42:37 | 200 | 50.421µs | 192.168.1.48 | GET "/api/ps" июл 18 21:42:37 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:42:37 | 200 | 9.612183ms | 192.168.1.48 | GET "/api/tags" июл 18 21:42:38 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:42:38 | 200 | 99.028µs | 192.168.1.48 | GET "/api/ps" июл 18 21:42:38 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:42:38 | 200 | 49.304µs | 192.168.1.48 | GET "/api/ps" июл 18 21:42:38 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:42:38 | 200 | 8.211767ms | 192.168.1.48 | GET "/api/tags" июл 18 21:42:59 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:42:59 | 200 | 78.079µs | 192.168.1.48 | GET "/api/ps" июл 18 21:42:59 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:42:59 | 200 | 48.887µs | 192.168.1.48 | GET "/api/ps" июл 18 21:42:59 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:42:59 | 200 | 6.733129ms | 192.168.1.48 | GET "/api/tags" июл 18 21:43:28 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:43:28 | 200 | 197.505µs | 192.168.1.48 | GET "/api/ps" июл 18 21:43:28 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:43:28 | 200 | 49.376µs | 192.168.1.48 | GET "/api/ps" июл 18 21:43:28 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:43:28 | 200 | 7.471603ms | 192.168.1.48 | GET "/api/tags" июл 18 21:44:36 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:44:36 | 200 | 117.822µs | 192.168.1.48 | GET "/api/ps" июл 18 21:44:36 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:44:36 | 200 | 50.076µs | 192.168.1.48 | GET "/api/ps" июл 18 21:44:36 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:44:36 | 200 | 7.978607ms | 192.168.1.48 | GET "/api/tags" июл 18 21:45:25 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:45:25 | 200 | 49.588µs | 192.168.1.48 | GET "/api/ps" июл 18 21:45:25 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:45:25 | 200 | 37.784µs | 192.168.1.48 | GET "/api/ps" июл 18 21:45:25 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:45:25 | 200 | 5.763366ms | 192.168.1.48 | GET "/api/tags" июл 18 21:45:51 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:45:51 | 200 | 71.238µs | 192.168.1.48 | GET "/api/ps" июл 18 21:45:51 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:45:51 | 200 | 87.441µs | 192.168.1.48 | GET "/api/ps" июл 18 21:45:51 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:45:51 | 200 | 7.298139ms | 192.168.1.48 | GET "/api/tags" июл 18 21:46:56 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:46:56 | 200 | 108.881µs | 192.168.1.48 | GET "/api/ps" июл 18 21:46:56 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:46:56 | 200 | 54.475µs | 192.168.1.48 | GET "/api/ps" июл 18 21:46:56 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:46:56 | 200 | 6.684716ms | 192.168.1.48 | GET "/api/tags" июл 18 21:47:28 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:47:28 | 200 | 77.244µs | 192.168.1.48 | GET "/api/ps" июл 18 21:47:28 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:47:28 | 200 | 50.076µs | 192.168.1.48 | GET "/api/ps" июл 18 21:47:28 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:47:28 | 200 | 8.869283ms | 192.168.1.48 | GET "/api/tags" июл 18 21:47:29 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:47:29 | 200 | 72.704µs | 192.168.1.48 | GET "/api/ps" июл 18 21:47:29 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:47:29 | 200 | 77.174µs | 192.168.1.48 | GET "/api/ps" июл 18 21:47:29 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:47:29 | 200 | 10.302346ms | 192.168.1.48 | GET "/api/tags" июл 18 21:48:09 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:48:09 | 200 | 87.371µs | 192.168.1.48 | GET "/api/ps" июл 18 21:48:09 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:48:09 | 200 | 60.203µs | 192.168.1.48 | GET "/api/ps" июл 18 21:48:09 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:48:09 | 200 | 8.397463ms | 192.168.1.48 | GET "/api/tags" июл 18 21:48:09 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:48:09 | 200 | 90.584µs | 192.168.1.48 | GET "/api/ps" июл 18 21:48:09 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:48:09 | 200 | 50.844µs | 192.168.1.48 | GET "/api/ps" июл 18 21:48:09 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:48:09 | 200 | 6.583135ms | 192.168.1.48 | GET "/api/tags" июл 18 21:48:10 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:48:10 | 200 | 70.33µs | 192.168.1.48 | GET "/api/ps" июл 18 21:48:10 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:48:10 | 200 | 70.609µs | 192.168.1.48 | GET "/api/ps" июл 18 21:48:10 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:48:10 | 200 | 6.514133ms | 192.168.1.48 | GET "/api/tags" июл 18 21:49:45 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:49:45 | 200 | 86.812µs | 192.168.1.48 | GET "/api/ps" июл 18 21:49:45 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:49:45 | 200 | 62.438µs | 192.168.1.48 | GET "/api/ps" июл 18 21:49:45 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:49:45 | 200 | 6.691764ms | 192.168.1.48 | GET "/api/tags" июл 18 21:50:03 dewiar-ai ollama[2420]: time=2025-07-18T21:50:03.278+03:00 level=INFO source=sched.go:788 msg="new model will fit in available VRAM in single GPU, loading" model=/usr/share/ollama/.ollama/models/blobs/sha256-3839a254cf2d00b208c6e2524c129e4438f9d106bba4c3fbc12b631f519d1de1 gpu=GPU-e7f8c414-e63e-8fb7-3de3-06dac76a4b04 parallel=2 available=49952456704 required="4.1 GiB" июл 18 21:50:03 dewiar-ai ollama[2420]: time=2025-07-18T21:50:03.457+03:00 level=INFO source=server.go:135 msg="system memory" total="188.6 GiB" free="183.9 GiB" free_swap="8.0 GiB" июл 18 21:50:03 dewiar-ai ollama[2420]: time=2025-07-18T21:50:03.640+03:00 level=INFO source=server.go:175 msg=offload library=cuda layers.requested=-1 layers.model=31 layers.offload=31 layers.split="" memory.available="[46.5 GiB]" memory.gpu_overhead="0 B" memory.required.full="4.1 GiB" memory.required.partial="4.1 GiB" memory.required.kv="120.0 MiB" memory.required.allocations="[4.1 GiB]" memory.weights.total="1.4 GiB" memory.weights.repeating="1.0 GiB" memory.weights.nonrepeating="420.4 MiB" memory.graph.full="2.0 GiB" memory.graph.partial="3.7 GiB" июл 18 21:50:03 dewiar-ai ollama[2420]: time=2025-07-18T21:50:03.640+03:00 level=INFO source=server.go:218 msg="enabling flash attention" июл 18 21:50:03 dewiar-ai ollama[2420]: time=2025-07-18T21:50:03.775+03:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-3839a254cf2d00b208c6e2524c129e4438f9d106bba4c3fbc12b631f519d1de1 --ctx-size 8192 --batch-size 512 --n-gpu-layers 31 --threads 8 --flash-attn --kv-cache-type q4_0 --parallel 2 --port 42047" июл 18 21:50:03 dewiar-ai ollama[2420]: time=2025-07-18T21:50:03.776+03:00 level=INFO source=sched.go:483 msg="loaded runners" count=1 июл 18 21:50:03 dewiar-ai ollama[2420]: time=2025-07-18T21:50:03.776+03:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding" июл 18 21:50:03 dewiar-ai ollama[2420]: time=2025-07-18T21:50:03.778+03:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding" июл 18 21:50:03 dewiar-ai ollama[2420]: time=2025-07-18T21:50:03.796+03:00 level=INFO source=runner.go:925 msg="starting ollama engine" июл 18 21:50:03 dewiar-ai ollama[2420]: time=2025-07-18T21:50:03.796+03:00 level=INFO source=runner.go:983 msg="Server listening on [127.0.0.1:42047](http://127.0.0.1:42047/)" июл 18 21:50:03 dewiar-ai ollama[2420]: time=2025-07-18T21:50:03.913+03:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3n file_type=Q4_K_M name="" description="" num_tensors=727 num_key_values=40 июл 18 21:50:04 dewiar-ai ollama[2420]: time=2025-07-18T21:50:04.033+03:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model" июл 18 21:50:04 dewiar-ai ollama[2420]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no июл 18 21:50:04 dewiar-ai ollama[2420]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no июл 18 21:50:04 dewiar-ai ollama[2420]: ggml_cuda_init: found 1 CUDA devices: июл 18 21:50:04 dewiar-ai ollama[2420]: Device 0: NVIDIA RTX A6000, compute capability 8.6, VMM: yes июл 18 21:50:04 dewiar-ai ollama[2420]: load_backend: loaded CUDA backend from /usr/local/lib/ollama/libggml-cuda.so июл 18 21:50:04 dewiar-ai ollama[2420]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-sandybridge.so июл 18 21:50:04 dewiar-ai ollama[2420]: time=2025-07-18T21:50:04.500+03:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc) июл 18 21:50:04 dewiar-ai ollama[2420]: time=2025-07-18T21:50:04.640+03:00 level=INFO source=ggml.go:359 msg="model weights" buffer=CUDA0 size="5.2 GiB" июл 18 21:50:04 dewiar-ai ollama[2420]: time=2025-07-18T21:50:04.641+03:00 level=INFO source=ggml.go:359 msg="model weights" buffer=CPU size="420.4 MiB" июл 18 21:50:04 dewiar-ai ollama[2420]: time=2025-07-18T21:50:04.658+03:00 level=INFO source=ggml.go:648 msg="compute graph" backend=CUDA0 buffer_type=CUDA0 size="79.0 MiB" июл 18 21:50:04 dewiar-ai ollama[2420]: time=2025-07-18T21:50:04.658+03:00 level=INFO source=ggml.go:648 msg="compute graph" backend=CPU buffer_type=CPU size="12.5 MiB" июл 18 21:50:23 dewiar-ai ollama[2420]: time=2025-07-18T21:50:23.385+03:00 level=INFO source=server.go:637 msg="llama runner started in 19.61 seconds" июл 18 21:50:24 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:50:24 | 200 | 22.239422255s | 192.168.1.48 | POST "/api/chat" июл 18 21:51:49 dewiar-ai ollama[2420]: [GIN] 2025/07/18 - 21:51:49 | 200 | 359.071409ms | 192.168.1.48 | POST "/api/chat"
GiteaMirror commented 2026-04-12 19:38:09 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 18, 2025):

This is a log showing gemma3n being loaded and answering two queries.

<!-- gh-comment-id:3090746185 --> @rick-github commented on GitHub (Jul 18, 2025): This is a log showing gemma3n being loaded and answering two queries.
GiteaMirror commented 2026-04-12 19:38:10 -05:00
Author
Owner
Copy Link

@DewiarQR commented on GitHub (Jul 18, 2025):

Everything is correct. I launched Gemma - got a correct response. Then I launched Qwen - and got a set of strange symbols in response. Then I copied this log and sent it to you... it turns out that Qwen not only does not work correctly, but also does not appear in the logs?

<!-- gh-comment-id:3090800165 --> @DewiarQR commented on GitHub (Jul 18, 2025): Everything is correct. I launched Gemma - got a correct response. Then I launched Qwen - and got a set of strange symbols in response. Then I copied this log and sent it to you... it turns out that Qwen not only does not work correctly, but also does not appear in the logs?
GiteaMirror commented 2026-04-12 19:38:10 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 18, 2025):

Set OLLAMA_DEBUG=1 in the server environment. Run qwen2.5vl. Run journalctl -u ollama --no-pager. Post the log.

<!-- gh-comment-id:3090918340 --> @rick-github commented on GitHub (Jul 18, 2025): Set `OLLAMA_DEBUG=1` in the server environment. Run qwen2.5vl. Run `journalctl -u ollama --no-pager`. Post the log.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#7535
Delete Branch "%!s()"

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