github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-22 21:51:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #7370] [Solved] Load and Unload model #51194

New Issue
Closed
opened 2026-04-28 18:54:10 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-28 18:54:10 -05:00
Owner
Copy Link

Originally created by @Khampol on GitHub (Oct 26, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7370

If I load a model then choose to load another one, looks like the 1st model is not unload ... ? Why ? 🤨 Is there a way to NOT keeping both as it use a LOT of my vram 😥

Originally created by @Khampol on GitHub (Oct 26, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7370 If I load a model then choose to load another one, looks like the 1st model is not unload ... ? Why ? 🤨 Is there a way to NOT keeping both as it use a LOT of my vram 😥
GiteaMirror added the question label 2026-04-28 18:54:10 -05:00
GiteaMirror commented 2026-04-28 18:54:11 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 26, 2024):

ollama will not evict a model if it doesn't have to - if they both fit in VRAM, ollama sees nothing wrong with loading both. If you want to evict a model before it's 5 minute timeout, you can use the stop command.

<!-- gh-comment-id:2439129333 --> @rick-github commented on GitHub (Oct 26, 2024): ollama will not evict a model if it doesn't have to - if they both fit in VRAM, ollama sees nothing wrong with loading both. If you want to evict a model before it's 5 minute timeout, you can use the [`stop`](https://github.com/ollama/ollama/blob/main/docs/faq.md#how-do-i-keep-a-model-loaded-in-memory-or-make-it-unload-immediately) command.
GiteaMirror commented 2026-04-28 18:54:11 -05:00
Author
Owner
Copy Link

@Khampol commented on GitHub (Oct 26, 2024):

Hi,
This is the solution, thanks a lot ! ❤️👍
It would be very useful to add a node for this for Comfyui !
( Ps : I use ollma and comfy at same time so very tight often on the vram )

<!-- gh-comment-id:2439145164 --> @Khampol commented on GitHub (Oct 26, 2024): Hi, This is the solution, thanks a lot ! ❤️👍 It would be very useful to add a node for this for Comfyui ! ( Ps : I use ollma and comfy at same time so very tight often on the vram )
GiteaMirror commented 2026-04-28 18:54:12 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Oct 28, 2024):

The behavior of the scheduler is configurable and documented here - https://github.com/ollama/ollama/blob/main/docs/faq.md#how-does-ollama-handle-concurrent-requests

<!-- gh-comment-id:2441947615 --> @dhiltgen commented on GitHub (Oct 28, 2024): The behavior of the scheduler is configurable and documented here - https://github.com/ollama/ollama/blob/main/docs/faq.md#how-does-ollama-handle-concurrent-requests
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label question
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#51194
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?