[GH-ISSUE #15804] Ollama show --modelfile no longer shows the full modelfile. #72131

Closed
opened 2026-05-05 03:31:17 -05:00 by GiteaMirror · 1 comment
Owner

Originally created by @chigkim on GitHub (Apr 24, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15804

What is the issue?

When I run ollama show qwen3.6:35b-a3b-q8_0 --modelfile>qwen36.modelfile, it does not save the full modelfile.
As a result, if I import a finetuned model with qwen36.modelfile, Ollama says the model does not support tools.
It used to show full template including tools and system message.

Relevant log output


OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.21.2

Originally created by @chigkim on GitHub (Apr 24, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15804 ### What is the issue? When I run `ollama show qwen3.6:35b-a3b-q8_0 --modelfile>qwen36.modelfile`, it does not save the full modelfile. As a result, if I import a finetuned model with qwen36.modelfile, Ollama says the model does not support tools. It used to show full template including tools and system message. ### Relevant log output ```shell ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.21.2
GiteaMirror added the bug label 2026-05-05 03:31:17 -05:00
Author
Owner

@chigkim commented on GitHub (Apr 25, 2026):

It looks like a different issue.

<!-- gh-comment-id:4318926090 --> @chigkim commented on GitHub (Apr 25, 2026): It looks like a different issue.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#72131