github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #12001] Only one models loaded into memory at once #7967

New Issue
Closed
opened 2026-04-12 20:09:02 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-04-12 20:09:02 -05:00
Owner
Copy Link

Originally created by @hteeyeoh on GitHub (Aug 21, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12001

What is the issue?

I have a pipline with load 1 embedding model and 1 llm models into memory for my RAG application. It was showing both model when using 'ollama ps' command when using 'ollama version 0.11.4' but now it only show the latest one which being triggered and load it into memory on version 0.11.5 which was totally different now. Is the the expected change? And how to keep both model load in the memory at the same time?

Im using pure cpu host which do not have GPU.

Relevant log output

OS

Linux

GPU

No response

CPU

Intel

Ollama version

0.11.5

Originally created by @hteeyeoh on GitHub (Aug 21, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12001 ### What is the issue? I have a pipline with load 1 embedding model and 1 llm models into memory for my RAG application. It was showing both model when using 'ollama ps' command when using 'ollama version 0.11.4' but now it only show the latest one which being triggered and load it into memory on version `0.11.5` which was totally different now. Is the the expected change? And how to keep both model load in the memory at the same time? Im using pure cpu host which do not have GPU. ### Relevant log output ```shell ``` ### OS Linux ### GPU _No response_ ### CPU Intel ### Ollama version 0.11.5
GiteaMirror added the bug label 2026-04-12 20:09:02 -05:00
GiteaMirror commented 2026-04-12 20:09:04 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Aug 21, 2025):

Hi @hteeyeoh sorry for the issue. This was fixed in 073fa31df5 and will be available in an update soon.

For now using 0.11.4 will work. to install it on Linux you can run:

curl -fsSL https://ollama.com/install.sh | OLLAMA_VERSION=0.11.4 sh
<!-- gh-comment-id:3209049448 --> @jmorganca commented on GitHub (Aug 21, 2025): Hi @hteeyeoh sorry for the issue. This was fixed in https://github.com/ollama/ollama/commit/073fa31df501d7cb943d3fa0fb19841da9651479 and will be available in an update soon. For now using `0.11.4` will work. to install it on Linux you can run: ``` curl -fsSL https://ollama.com/install.sh | OLLAMA_VERSION=0.11.4 sh ```
GiteaMirror commented 2026-04-12 20:09:05 -05:00
Author
Owner
Copy Link

@hteeyeoh commented on GitHub (Aug 21, 2025):

Hi @hteeyeoh sorry for the issue. This was fixed in 073fa31 and will be available in an update soon.

For now using 0.11.4 will work. to install it on Linux you can run:

curl -fsSL https://ollama.com/install.sh | OLLAMA_VERSION=0.11.4 sh

No issue. Would just like to understand whether this is a bug or this would be the expected behaviour going forward.

Thanks for your quick reply.

<!-- gh-comment-id:3209054542 --> @hteeyeoh commented on GitHub (Aug 21, 2025): > Hi [@hteeyeoh](https://github.com/hteeyeoh) sorry for the issue. This was fixed in [073fa31](https://github.com/ollama/ollama/commit/073fa31df501d7cb943d3fa0fb19841da9651479) and will be available in an update soon. > > For now using `0.11.4` will work. to install it on Linux you can run: > > ``` > curl -fsSL https://ollama.com/install.sh | OLLAMA_VERSION=0.11.4 sh > ``` No issue. Would just like to understand whether this is a bug or this would be the expected behaviour going forward. Thanks for your quick reply.
GiteaMirror commented 2026-04-12 20:09:06 -05:00
Author
Owner
Copy Link

@FieldMouse-AI commented on GitHub (Aug 21, 2025):

@jmorganca ,

@hteeyeoh 's issue actually looks like a continuation of the issue that I had opened recently: https://github.com/ollama/ollama/issues/11974

I tested v0.11.06 and found that problem appears to still persist, but looking at https://github.com/ollama/ollama/issues/11974, I was under the impression that it was fixed. Am I mistaken? 🤔

Thanks for your help and all. 🤗

<!-- gh-comment-id:3210152073 --> @FieldMouse-AI commented on GitHub (Aug 21, 2025): @jmorganca , @hteeyeoh 's issue actually looks like a continuation of the issue that I had opened recently: https://github.com/ollama/ollama/issues/11974 I tested v0.11.06 and found that problem appears to still persist, but looking at https://github.com/ollama/ollama/issues/11974, I was under the impression that it was fixed. Am I mistaken? 🤔 Thanks for your help and all. 🤗
GiteaMirror commented 2026-04-12 20:09:07 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Aug 21, 2025):

0.11.6 doesn't include 073fa31df5.

<!-- gh-comment-id:3211333121 --> @rick-github commented on GitHub (Aug 21, 2025): 0.11.6 doesn't include https://github.com/ollama/ollama/commit/073fa31df501d7cb943d3fa0fb19841da9651479.
GiteaMirror commented 2026-04-12 20:09:08 -05:00
Author
Owner
Copy Link

@FieldMouse-AI commented on GitHub (Aug 21, 2025):

0.11.6 doesn't include 073fa31.

Ah, I see, 073fa31df5 is not in 0.11.6, but will arrive in a future release.

I was qute worried as the constant model reloads cause around a 3x slowdown of some some inferences.

I will remain on 0.11.4 until 073fa31df5 is integrated into a release.

If you would like to request that I retest it (like during a release candidate or something like that), please let me know. 🤗

Thanks! 🤗

<!-- gh-comment-id:3211820342 --> @FieldMouse-AI commented on GitHub (Aug 21, 2025): > 0.11.6 doesn't include [073fa31](https://github.com/ollama/ollama/commit/073fa31df501d7cb943d3fa0fb19841da9651479). Ah, I see, https://github.com/ollama/ollama/commit/073fa31df501d7cb943d3fa0fb19841da9651479 is not in 0.11.6, but will arrive in a future release. I was qute worried as the constant model reloads cause around a 3x slowdown of some some inferences. I will remain on 0.11.4 until https://github.com/ollama/ollama/commit/073fa31df501d7cb943d3fa0fb19841da9651479 is integrated into a release. If you would like to request that I retest it (like during a release candidate or something like that), please let me know. 🤗 Thanks! 🤗
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 bug
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#7967
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?