[GH-ISSUE #13620] qwen3-vl disable thinking #55475

Closed
opened 2026-04-29 09:16:51 -05:00 by GiteaMirror · 1 comment
Owner

Originally created by @jw-redpanda on GitHub (Jan 4, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/13620

Trying out the qwen3-vl model, and it will output thinking response. Even though I place /no_think in the prompt, it has no effect. Wondering if there are ollama CLI options or whatever settings to disable thinking?

Originally created by @jw-redpanda on GitHub (Jan 4, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/13620 Trying out the qwen3-vl model, and it will output thinking response. Even though I place `/no_think` in the prompt, it has no effect. Wondering if there are ollama CLI options or whatever settings to disable thinking?
Author
Owner

@rick-github commented on GitHub (Jan 4, 2026):

Use the non thinking version of the model.

<!-- gh-comment-id:3708169022 --> @rick-github commented on GitHub (Jan 4, 2026): Use the [non thinking version](https://ollama.com/library/qwen3-vl:8b-instruct-q4_K_M) of the model.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#55475