[GH-ISSUE #12882] 10x slower Qwen3 and 2.5 VL #34296

Closed
opened 2026-04-22 17:44:23 -05:00 by GiteaMirror · 4 comments
Owner

Originally created by @ai-joe-git on GitHub (Oct 31, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12882

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

Qwen 2.5 VL and Qwen 3 VL have become so slow since the last update that they are barely usable!

Relevant log output


OS

Windows

GPU

Intel

CPU

Intel

Ollama version

No response

Originally created by @ai-joe-git on GitHub (Oct 31, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12882 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? Qwen 2.5 VL and Qwen 3 VL have become so slow since the last update that they are barely usable! ### Relevant log output ```shell ``` ### OS Windows ### GPU Intel ### CPU Intel ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-22 17:44:23 -05:00
Author
Owner

@josephlugo commented on GitHub (Oct 31, 2025):

Qwen3 models in general have become much slower.

<!-- gh-comment-id:3472721060 --> @josephlugo commented on GitHub (Oct 31, 2025): Qwen3 models in general have become much slower.
Author
Owner

@rick-github commented on GitHub (Oct 31, 2025):

Server log will help in debugging.

<!-- gh-comment-id:3473010684 --> @rick-github commented on GitHub (Oct 31, 2025): [Server log](https://docs.ollama.com/troubleshooting) will help in debugging.
Author
Owner

@rick-github commented on GitHub (Oct 31, 2025):

#12886

<!-- gh-comment-id:3473623685 --> @rick-github commented on GitHub (Oct 31, 2025): #12886
Author
Owner

@dhiltgen commented on GitHub (Oct 31, 2025):

Fix will be in 0.12.9

<!-- gh-comment-id:3474976566 --> @dhiltgen commented on GitHub (Oct 31, 2025): Fix will be in 0.12.9
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#34296