[GH-ISSUE #15268] No thinking for gemma4 with /api/generate by default #9765

Open
opened 2026-04-12 22:39:17 -05:00 by GiteaMirror · 0 comments
Owner

Originally created by @Nix-01 on GitHub (Apr 3, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15268

What is the issue?

Thinking works fine for gemma4 with /api/chat but don't with /api/generate

Thinking works with /api/generate if we force it in the payload (think: True).

This behavior is reversed with other models like qwen3 (think by default)

Relevant log output


OS

Windows

GPU

Nvidia

CPU

AMD

Ollama version

0.20.0

Originally created by @Nix-01 on GitHub (Apr 3, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15268 ### What is the issue? Thinking works fine for gemma4 with /api/chat but don't with /api/generate Thinking works with /api/generate if we force it in the payload (think: True). This behavior is reversed with other models like qwen3 (think by default) ### Relevant log output ```shell ``` ### OS Windows ### GPU Nvidia ### CPU AMD ### Ollama version 0.20.0
GiteaMirror added the bug label 2026-04-12 22:39:17 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#9765