[GH-ISSUE #4340] how can I make ollama always run models? #2703

Closed
opened 2026-04-12 13:01:24 -05:00 by GiteaMirror · 3 comments
Owner

Originally created by @zhaoyuchen1128 on GitHub (May 11, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4340

What is the issue?

If the model does not run for a while, the model will stop and reloading will consume a lot of time.So the user experience is not good

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @zhaoyuchen1128 on GitHub (May 11, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4340 ### What is the issue? If the model does not run for a while, the model will stop and reloading will consume a lot of time.So the user experience is not good ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the question label 2026-04-12 13:01:24 -05:00
Author
Owner

@taozhiyuai commented on GitHub (May 11, 2024):

已经处理过这个问题,搜索一下

<!-- gh-comment-id:2105557724 --> @taozhiyuai commented on GitHub (May 11, 2024): 已经处理过这个问题,搜索一下
Author
Owner

@dhiltgen commented on GitHub (Jul 25, 2024):

You can control how long the model stays loaded with keep_alive - see https://github.com/ollama/ollama/blob/main/docs/faq.md#how-do-i-keep-a-model-loaded-in-memory-or-make-it-unload-immediately

<!-- gh-comment-id:2251198634 --> @dhiltgen commented on GitHub (Jul 25, 2024): You can control how long the model stays loaded with keep_alive - see https://github.com/ollama/ollama/blob/main/docs/faq.md#how-do-i-keep-a-model-loaded-in-memory-or-make-it-unload-immediately
Author
Owner

@hello1337lol commented on GitHub (Feb 8, 2026):

sorry, but the faq is offline

<!-- gh-comment-id:3866313171 --> @hello1337lol commented on GitHub (Feb 8, 2026): sorry, but the faq is offline
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#2703