[GH-ISSUE #6720] Can you specify a graphics card in the ollama deployment model? #4232

Open
opened 2026-04-12 15:10:08 -05:00 by GiteaMirror · 1 comment
Owner

Originally created by @LIUKAI0815 on GitHub (Sep 10, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6720

For example, qwen2 is in CUDA_VISIBLE_DEVICE=2 and glm4 is in CUDA_VISIBLE_DEVICE=4

Originally created by @LIUKAI0815 on GitHub (Sep 10, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6720 For example, qwen2 is in CUDA_VISIBLE_DEVICE=2 and glm4 is in CUDA_VISIBLE_DEVICE=4
GiteaMirror added the feature request label 2026-04-12 15:10:08 -05:00
Author
Owner

@rick-github commented on GitHub (Sep 10, 2024):

You can do this if you run a separate ollama instance for each graphics card.

<!-- gh-comment-id:2340022122 --> @rick-github commented on GitHub (Sep 10, 2024): You can do this if you run a separate ollama instance for each graphics card.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#4232