github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #10762] Ollama keeps flushing Qwen3 from memory every prompt #7070

New Issue
Closed
opened 2026-04-12 18:59:41 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 18:59:41 -05:00
Owner
Copy Link

Originally created by @codecrafting-io on GitHub (May 18, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10762

What is the issue?

I have an issue since Qwen3 14B public launch, that for every prompt the model is beign flushed from memory, which is the main cause for bad performance for this model I think. I have tried several versions from 0.6.6 to the latest 0.7.0. I'm using ollama in conjunction with Open Webui, but I don't see this behavior for other models, like Deepseek R1 and Gemma 3. I know there is a keep alive setting, but my goal is not to leave the model in memory indefinitely, and it should stay in memory for at least a few minutes, just like other models do.

I'm using a RTX 4060TI 16GB and I'm not sure what's going on, but to date the issue is still happening.

Relevant log output

OS

Linux

GPU

Nvidia

CPU

AMD

Ollama version

0.7.0

Originally created by @codecrafting-io on GitHub (May 18, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10762 ### What is the issue? I have an issue since Qwen3 14B public launch, that for every prompt the model is beign flushed from memory, which is the main cause for bad performance for this model I think. I have tried several versions from 0.6.6 to the latest 0.7.0. I'm using ollama in conjunction with Open Webui, but I don't see this behavior for other models, like Deepseek R1 and Gemma 3. I know there is a keep alive setting, but my goal is not to leave the model in memory indefinitely, and it should stay in memory for at least a few minutes, just like other models do. I'm using a RTX 4060TI 16GB and I'm not sure what's going on, but to date the issue is still happening. ### Relevant log output ```shell ``` ### OS Linux ### GPU Nvidia ### CPU AMD ### Ollama version 0.7.0
GiteaMirror added the bugneeds more info labels 2026-04-12 18:59:41 -05:00
GiteaMirror commented 2026-04-12 18:59:43 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (May 18, 2025):

Server logs may aid in debugging.

<!-- gh-comment-id:2888858444 --> @rick-github commented on GitHub (May 18, 2025): [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) may aid in debugging.
GiteaMirror commented 2026-04-12 18:59:43 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (May 20, 2025):

When you use ollama ps after a prompt, what does it say?

<!-- gh-comment-id:2896076246 --> @pdevine commented on GitHub (May 20, 2025): When you use `ollama ps` after a prompt, what does it say?
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 needs more info
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#7070
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?