[GH-ISSUE #1929] WARNING: No NVIDIA GPU detected. Ollama will run in CPU-only mode. #26871

Closed
opened 2026-04-22 03:34:27 -05:00 by GiteaMirror · 2 comments
Owner

Originally created by @xzkxzk12301230 on GitHub (Jan 11, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/1929

Originally assigned to: @dhiltgen on GitHub.

i use wsl2,and GPU information is as follows. when i install ollama,it WARNING: No NVIDIA GPU detected. Ollama will run in CPU-only mode.
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 546.33 Driver Version: 546.33 CUDA Version: 12.3 |
|-----------------------------------------+----------------------+----------------------+
| GPU Name TCC/WDDM | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+======================+======================|
| 0 NVIDIA GeForce RTX 4060 Ti WDDM | 00000000:03:00.0 On | N/A |
| 0% 29C P8 7W / 180W | 581MiB / 16380MiB | 0% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+

Originally created by @xzkxzk12301230 on GitHub (Jan 11, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/1929 Originally assigned to: @dhiltgen on GitHub. i use wsl2,and GPU information is as follows. when i install ollama,it WARNING: No NVIDIA GPU detected. Ollama will run in CPU-only mode. +---------------------------------------------------------------------------------------+ | NVIDIA-SMI 546.33 Driver Version: 546.33 CUDA Version: 12.3 | |-----------------------------------------+----------------------+----------------------+ | GPU Name TCC/WDDM | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |=========================================+======================+======================| | 0 NVIDIA GeForce RTX 4060 Ti WDDM | 00000000:03:00.0 On | N/A | | 0% 29C P8 7W / 180W | 581MiB / 16380MiB | 0% Default | | | | N/A | +-----------------------------------------+----------------------+----------------------+
GiteaMirror added the nvidiabug labels 2026-04-22 03:34:27 -05:00
Author
Owner

@clianor commented on GitHub (Jan 14, 2024):

I tried to use ollama as wsl2 but I had the same problem.
So I ran the olama with docker and it worked well.
Here's the official ollama article for your reference.
https://ollama.ai/blog/ollama-is-now-available-as-an-official-docker-image

<!-- gh-comment-id:1890941649 --> @clianor commented on GitHub (Jan 14, 2024): I tried to use ollama as wsl2 but I had the same problem. So I ran the olama with docker and it worked well. Here's the official ollama article for your reference. https://ollama.ai/blog/ollama-is-now-available-as-an-official-docker-image
Author
Owner

@dhiltgen commented on GitHub (Jan 27, 2024):

@xzkxzk12301230 if you're still facing this problem, can you share the server log? It may also be helpful to run with OLLAMA_DEBUG=1 set to increase the verbosity of the logs.

https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues

<!-- gh-comment-id:1912860329 --> @dhiltgen commented on GitHub (Jan 27, 2024): @xzkxzk12301230 if you're still facing this problem, can you share the server log? It may also be helpful to run with `OLLAMA_DEBUG=1` set to increase the verbosity of the logs. https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#26871