[GH-ISSUE #5696] The model cannot be loaded into the gpu #65587

Closed
opened 2026-05-03 21:47:57 -05:00 by GiteaMirror · 2 comments
Owner

Originally created by @IanNOV13 on GitHub (Jul 15, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5696

Originally assigned to: @jmorganca on GitHub.

What is the issue?

After updating to version 0.2.5, the gemma2:9b model cannot be loaded into the GPU.
After I downgraded the version back to 0.2.4, the model was successfully loaded into the GPU.

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.2.5

Originally created by @IanNOV13 on GitHub (Jul 15, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5696 Originally assigned to: @jmorganca on GitHub. ### What is the issue? After updating to version 0.2.5, the gemma2:9b model cannot be loaded into the GPU. After I downgraded the version back to 0.2.4, the model was successfully loaded into the GPU. ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.2.5
GiteaMirror added the bug label 2026-05-03 21:47:57 -05:00
Author
Owner

@jmorganca commented on GitHub (Jul 15, 2024):

Hi there, try re-pulling the model: ollama pull gemma2:9b

May I ask what ollama ps shows for you with gemma2:9b loaded? Sorry you hit this issue

<!-- gh-comment-id:2227740637 --> @jmorganca commented on GitHub (Jul 15, 2024): Hi there, try re-pulling the model: `ollama pull gemma2:9b` May I ask what `ollama ps` shows for you with `gemma2:9b` loaded? Sorry you hit this issue
Author
Owner

@IanNOV13 commented on GitHub (Jul 15, 2024):

I reinstalled Ollama and it worked.

<!-- gh-comment-id:2227755462 --> @IanNOV13 commented on GitHub (Jul 15, 2024): I reinstalled Ollama and it worked.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#65587