[GH-ISSUE #15803] Ollama create doesn't clean up after importing. #72130

Open
opened 2026-05-05 03:31:14 -05:00 by GiteaMirror · 0 comments
Owner

Originally created by @chigkim on GitHub (Apr 24, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15803

What is the issue?

After I imported a finetuned qwen-3.6-35b in safetensor, it did not clean up the original model.
Blobs folder becomes really big.
This was fixed a while ago, but it looks like it got broken again.
Also, if ollama create fails due to lack of storage, next time when it launches, it used to clean up the broken files, but no longer clean that up either.

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/15803 ### What is the issue? After I imported a finetuned qwen-3.6-35b in safetensor, it did not clean up the original model. Blobs folder becomes really big. This was fixed a while ago, but it looks like it got broken again. Also, if ollama create fails due to lack of storage, next time when it launches, it used to clean up the broken files, but no longer clean that up either. ### Relevant log output ```shell ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.21.2
GiteaMirror added the bug label 2026-05-05 03:31:14 -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#72130