[GH-ISSUE #9206] Is there any way to keep some popular models being loaded in memory #5998

Closed
opened 2026-04-12 17:21:02 -05:00 by GiteaMirror · 1 comment
Owner

Originally created by @saeya211 on GitHub (Feb 19, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9206

ollama config: OLLAMA_MAX_LOADED_MODELS=5

For example:
We have 10 models managed by ollama, and model-A, model-B are most used daily.
So we wanna to model-A, model-B are always loaded, other models are loaded/unloaded as usual.

Is there any way or configuration can support this feature?

Originally created by @saeya211 on GitHub (Feb 19, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9206 ollama config: OLLAMA_MAX_LOADED_MODELS=5 For example: We have 10 models managed by ollama, and model-A, model-B are most used daily. So we wanna to model-A, model-B are always loaded, other models are loaded/unloaded as usual. Is there any way or configuration can support this feature?
GiteaMirror added the question label 2026-04-12 17:21:02 -05:00
Author
Owner

@pdevine commented on GitHub (Feb 19, 2025):

Thanks for the question. This is covered in the FAQ.

I'll go ahead and close the issue.

<!-- gh-comment-id:2667915045 --> @pdevine commented on GitHub (Feb 19, 2025): Thanks for the question. This is covered in the [FAQ](https://github.com/ollama/ollama/blob/main/docs/faq.md#how-do-i-keep-a-model-loaded-in-memory-or-make-it-unload-immediately). I'll go ahead and close the issue.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#5998