[GH-ISSUE #11055] Ollama uses CPU only after upgrading to CUDA 12.8 #7293

Closed
opened 2026-04-12 19:20:38 -05:00 by GiteaMirror · 1 comment
Owner

Originally created by @NEWbie0709 on GitHub (Jun 12, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11055

What is the issue?

After upgrading to CUDA 12.8 (from a previously working CUDA setup), Ollama now runs models using the CPU only, whereas it previously utilized the GPU at 100%. No changes were made to the model or Ollama configuration besides the CUDA upgrade.

Image

💻 System Info:

GPU: 3× NVIDIA GTX 1080 Ti

CUDA Version: 12.8

NVIDIA Driver Version: 570.86.10

OS: Ubuntu 20.04.5 LTS

ollama version is 0.9.0

Originally created by @NEWbie0709 on GitHub (Jun 12, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11055 ### What is the issue? After upgrading to CUDA 12.8 (from a previously working CUDA setup), Ollama now runs models using the CPU only, whereas it previously utilized the GPU at 100%. No changes were made to the model or Ollama configuration besides the CUDA upgrade. ![Image](https://github.com/user-attachments/assets/df631463-6009-4e5e-8ce0-2f745ffbfdff) 💻 System Info: ``` GPU: 3× NVIDIA GTX 1080 Ti CUDA Version: 12.8 NVIDIA Driver Version: 570.86.10 OS: Ubuntu 20.04.5 LTS ollama version is 0.9.0 ```
GiteaMirror added the bugneeds more info labels 2026-04-12 19:20:38 -05:00
Author
Owner

@rick-github commented on GitHub (Jun 12, 2025):

Server logs will aid in debugging.

<!-- gh-comment-id:2965893696 --> @rick-github commented on GitHub (Jun 12, 2025): [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) will aid in debugging.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#7293