github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 00:51:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #7168] ollama process uses 1 gb of memory when it's idle due to embedded runners #4550

New Issue
Closed
opened 2026-04-12 15:29:29 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-12 15:29:29 -05:00
Owner
Copy Link

Originally created by @kha84 on GitHub (Oct 10, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7168

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

user@magicbook14:~$ ollama --version
ollama version is 0.3.12
user@magicbook14:~$ ollama ps
NAME    ID    SIZE    PROCESSOR    UNTIL

image

I'm pretty sure it's some kind of regress, because on previous versions I didn't notice that high memory usage when no models were loaded. The system it's running on is laptop with AMD Ryzen 7 APU - 5700, no discreet GPU is there, just an integrated one in CPU

OS

Linux

GPU

AMD

CPU

AMD

Ollama version

0.3.12

Originally created by @kha84 on GitHub (Oct 10, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7168 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? ``` user@magicbook14:~$ ollama --version ollama version is 0.3.12 user@magicbook14:~$ ollama ps NAME ID SIZE PROCESSOR UNTIL ``` ![image](https://github.com/user-attachments/assets/05de0a19-b087-4c5a-ba45-f5ae421ed9a7) I'm pretty sure it's some kind of regress, because on previous versions I didn't notice that high memory usage when no models were loaded. The system it's running on is laptop with AMD Ryzen 7 APU - 5700, no discreet GPU is there, just an integrated one in CPU ### OS Linux ### GPU AMD ### CPU AMD ### Ollama version 0.3.12
GiteaMirror added the linuxfeature request labels 2026-04-12 15:29:29 -05:00
GiteaMirror commented 2026-04-12 15:29:30 -05:00
Author
Owner
Copy Link

@taskylizard commented on GitHub (Oct 11, 2024):

Same issue here as well.

<!-- gh-comment-id:2407224397 --> @taskylizard commented on GitHub (Oct 11, 2024): Same issue here as well.
GiteaMirror commented 2026-04-12 15:29:31 -05:00
Author
Owner
Copy Link

@kha84 commented on GitHub (Oct 11, 2024):

I have another installation with older version 0.3.11 and there it takes just few tens of Mb:

user@7940hs:~$ ollama --version
ollama version is 0.3.11

image

<!-- gh-comment-id:2407602434 --> @kha84 commented on GitHub (Oct 11, 2024): I have another installation with older version 0.3.11 and there it takes just few tens of Mb: ``` user@7940hs:~$ ollama --version ollama version is 0.3.11 ``` ![image](https://github.com/user-attachments/assets/adb20b7d-9b33-485a-84ef-f6d1eb973949)
GiteaMirror commented 2026-04-12 15:29:31 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 11, 2024):

Size of the server grows because of changes to the runners.

$ ps -C "$(echo ollama:0.3.{0..12})" -o comm,rss
COMMAND           RSS
ollama:0.3.0    576792
ollama:0.3.1    575288
ollama:0.3.2    575684
ollama:0.3.3    516652
ollama:0.3.4    577476
ollama:0.3.5    574996
ollama:0.3.6    576004
ollama:0.3.7    889928
ollama:0.3.8    886236
ollama:0.3.9    885652
ollama:0.3.10   1040208
ollama:0.3.11   1048308
ollama:0.3.12   1045592

ollama:0.3.7 was the introduction of the cuda_v12 runner. ollama:0.3.10 pulled in a new version of llama.cpp causing the size of libggml.so to increase.

<!-- gh-comment-id:2407889238 --> @rick-github commented on GitHub (Oct 11, 2024): Size of the server grows because of changes to the runners. ```console $ ps -C "$(echo ollama:0.3.{0..12})" -o comm,rss COMMAND RSS ollama:0.3.0 576792 ollama:0.3.1 575288 ollama:0.3.2 575684 ollama:0.3.3 516652 ollama:0.3.4 577476 ollama:0.3.5 574996 ollama:0.3.6 576004 ollama:0.3.7 889928 ollama:0.3.8 886236 ollama:0.3.9 885652 ollama:0.3.10 1040208 ollama:0.3.11 1048308 ollama:0.3.12 1045592 ``` ollama:0.3.7 was the introduction of the [cuda_v12](https://github.com/ollama/ollama/commit/4fe3a556faf790ba993223cfdda16e281b6cb76d) runner. ollama:0.3.10 [pulled](https://github.com/ollama/ollama/commit/5e2653f9fe454e948a8d48e3c15c21830c1ac26b) in a new version of llama.cpp causing the size of libggml.so to increase.
GiteaMirror commented 2026-04-12 15:29:31 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Apr 19, 2025):

COMMAND           RSS
ollama:0.3.0    590152
ollama:0.3.1    588480
ollama:0.3.2    589428
ollama:0.3.3    587956
ollama:0.3.4    591080
ollama:0.3.5    590044
ollama:0.3.6    588816
ollama:0.3.7    903948
ollama:0.3.8    903636
ollama:0.3.9    903632
ollama:0.3.10   1060860
ollama:0.3.11   1065592
ollama:0.3.12   1066252
ollama:0.3.13   1067664
ollama:0.3.14   1068712
ollama:0.4.0    65512
ollama:0.4.1    66768
ollama:0.4.2    66708
ollama:0.4.3    62316
ollama:0.4.4    63300
ollama:0.4.5    67036
ollama:0.4.6    69512
ollama:0.4.7    66792
ollama:0.5.0    65468
ollama:0.5.1    69136
ollama:0.5.2    46620
ollama:0.5.3    46392
ollama:0.5.4    46336
ollama:0.5.5    45768
ollama:0.5.6    46100
ollama:0.5.7    46040
ollama:0.5.8    45944
ollama:0.5.9    46676
ollama:0.5.10   45668
ollama:0.5.11   46860
ollama:0.5.12   48036
ollama:0.5.13   47332
ollama:0.6.0    46520
ollama:0.6.1    46896
ollama:0.6.2    47508
ollama:0.6.3    47304
ollama:0.6.4    47000
ollama:0.6.5    46592
ollama:0.6.6    47548
<!-- gh-comment-id:2816841432 --> @rick-github commented on GitHub (Apr 19, 2025): ``` COMMAND RSS ollama:0.3.0 590152 ollama:0.3.1 588480 ollama:0.3.2 589428 ollama:0.3.3 587956 ollama:0.3.4 591080 ollama:0.3.5 590044 ollama:0.3.6 588816 ollama:0.3.7 903948 ollama:0.3.8 903636 ollama:0.3.9 903632 ollama:0.3.10 1060860 ollama:0.3.11 1065592 ollama:0.3.12 1066252 ollama:0.3.13 1067664 ollama:0.3.14 1068712 ollama:0.4.0 65512 ollama:0.4.1 66768 ollama:0.4.2 66708 ollama:0.4.3 62316 ollama:0.4.4 63300 ollama:0.4.5 67036 ollama:0.4.6 69512 ollama:0.4.7 66792 ollama:0.5.0 65468 ollama:0.5.1 69136 ollama:0.5.2 46620 ollama:0.5.3 46392 ollama:0.5.4 46336 ollama:0.5.5 45768 ollama:0.5.6 46100 ollama:0.5.7 46040 ollama:0.5.8 45944 ollama:0.5.9 46676 ollama:0.5.10 45668 ollama:0.5.11 46860 ollama:0.5.12 48036 ollama:0.5.13 47332 ollama:0.6.0 46520 ollama:0.6.1 46896 ollama:0.6.2 47508 ollama:0.6.3 47304 ollama:0.6.4 47000 ollama:0.6.5 46592 ollama:0.6.6 47548 ```
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 feature request linux
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#4550
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?