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 #10367] Slow progressive memory usage increase (Ollama server) #6811

New Issue
Closed
opened 2026-04-12 18:35:52 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 18:35:52 -05:00
Owner
Copy Link

Originally created by @Belluxx on GitHub (Apr 22, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10367

What is the issue?

I am running Ollama with OLLAMA_KEEP_ALIVE 1m and OLLAMA_CONTEXT_LENGTH "8192".
Model tested: Gemma 3 27B Q4 QAT

The server is receiving around 1 request per minute (sequentially, only one at a time), and i am seeing an increase from the initial 30GB of RAM usage (right after starting the server) up to 50GB 3/4 hours later (so after hundreds of requests). It is continuing to rise, and appears to be a linear slow increase.

Maybe this due to prompt caching not discarding old cached prompts?

Relevant log output

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.6.5

Originally created by @Belluxx on GitHub (Apr 22, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10367 ### What is the issue? I am running Ollama with `OLLAMA_KEEP_ALIVE 1m` and `OLLAMA_CONTEXT_LENGTH "8192"`. Model tested: `Gemma 3 27B Q4 QAT` The server is receiving around 1 request per minute (sequentially, only one at a time), and i am seeing an increase from the initial 30GB of RAM usage (right after starting the server) up to 50GB 3/4 hours later (so after hundreds of requests). It is continuing to rise, and appears to be a linear slow increase. Maybe this due to prompt caching not discarding old cached prompts? ### Relevant log output ```shell ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.6.5
GiteaMirror added the bug label 2026-04-12 18:35:52 -05:00
GiteaMirror commented 2026-04-12 18:35:53 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Apr 22, 2025):

#10040

<!-- gh-comment-id:2821022962 --> @rick-github commented on GitHub (Apr 22, 2025): #10040
GiteaMirror commented 2026-04-12 18:35:54 -05:00
Author
Owner
Copy Link

@Belluxx commented on GitHub (Apr 22, 2025):

Sorry, i tried to search for similar issues and didn't find that one. I see that a fix was already pushed but it will be released in the next versions, thanks!

<!-- gh-comment-id:2821065321 --> @Belluxx commented on GitHub (Apr 22, 2025): Sorry, i tried to search for similar issues and didn't find that one. I see that a fix was already pushed but it will be released in the next versions, 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#6811
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?