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 #10076] Ollama doesn't release RAM #68662

New Issue
Open
opened 2026-05-04 14:46:46 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-05-04 14:46:46 -05:00
Owner
Copy Link

Originally created by @ayushkevich on GitHub (Apr 1, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10076

What is the issue?

I have the following PC configuration:

  1. CPU: AMD Ryzen 7700
  2. GPU: GeForce RTX 3060 12 GB
  3. RAM: 32 GB

I attempted to run QwQ:32b in ollama inside docker container. It filled almost all RAM. RAM wasn't cleared after the model execution. I checked docker stats and I found that ollama container uses 20 GB RAM. I attempted to stop model inside container and restart container but docker stats show that ollama container uses < 1 GB RAM, however the system sees 20 GB usage.
Can anybody help me with fixing this issue?

Relevant log output

CONTAINER ID   NAME         CPU %     MEM USAGE / LIMIT     MEM %     NET I/O           BLOCK I/O        PIDS
ed751f322c16   open-webui   0.10%     746.4MiB / 30.46GiB   2.39%     25.9kB / 7.07kB   422MB / 12.3kB   38
519abddc8517   ollama       0.00%     18MiB / 30.46GiB      0.06%     5.91kB / 126B     0B / 0B          12

Image

OS

Linux

GPU

Nvidia

CPU

AMD

Ollama version

0.6.2

Originally created by @ayushkevich on GitHub (Apr 1, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10076 ### What is the issue? I have the following PC configuration: 1. CPU: AMD Ryzen 7700 2. GPU: GeForce RTX 3060 12 GB 3. RAM: 32 GB I attempted to run QwQ:32b in ollama inside docker container. It filled almost all RAM. RAM wasn't cleared after the model execution. I checked docker stats and I found that ollama container uses 20 GB RAM. I attempted to stop model inside container and restart container but docker stats show that ollama container uses < 1 GB RAM, however the system sees 20 GB usage. Can anybody help me with fixing this issue? ### Relevant log output ```shell CONTAINER ID NAME CPU % MEM USAGE / LIMIT MEM % NET I/O BLOCK I/O PIDS ed751f322c16 open-webui 0.10% 746.4MiB / 30.46GiB 2.39% 25.9kB / 7.07kB 422MB / 12.3kB 38 519abddc8517 ollama 0.00% 18MiB / 30.46GiB 0.06% 5.91kB / 126B 0B / 0B 12 ``` ![Image](https://github.com/user-attachments/assets/88bf75c1-f03c-4c45-a0de-3a71553bd920) ### OS Linux ### GPU Nvidia ### CPU AMD ### Ollama version 0.6.2
GiteaMirror added the bug label 2026-05-04 14:46:46 -05:00
GiteaMirror commented 2026-05-04 14:46:49 -05:00
Author
Owner
Copy Link

@ayushkevich commented on GitHub (Apr 2, 2025):

I attempted to use ollama 0.6.3 and gemma 27b and it works fine. I attempted to use QwQ and here is the result of console commands execution:

~$ docker stats --no-stream
CONTAINER ID   NAME         CPU %     MEM USAGE / LIMIT     MEM %     NET I/O           BLOCK I/O         PIDS
0dd08cb728c4   ollama       0.13%     20.1GiB / 30.46GiB    66.01%    18.2GB / 462MB    41.9GB / 17.9GB   37
ed751f322c16   open-webui   0.10%     67.11MiB / 30.46GiB   0.22%     1.62MB / 6.84MB   660MB / 539MB     39
~$ docker stop ollama
ollama
~$ docker start ollama
ollama
~$ docker stats --no-stream
CONTAINER ID   NAME         CPU %     MEM USAGE / LIMIT     MEM %     NET I/O           BLOCK I/O       PIDS
0dd08cb728c4   ollama       0.00%     18.4MiB / 30.46GiB    0.06%     3.75kB / 126B     53.2kB / 0B     11
ed751f322c16   open-webui   0.08%     67.16MiB / 30.46GiB   0.22%     1.62MB / 6.85MB   660MB / 539MB   39
~$ free
               total        used        free      shared  buff/cache   available
Mem:        31935044    16048308     5755192       69300    10662744    15886736
Swap:        8099836     3333888     4765948
<!-- gh-comment-id:2772066221 --> @ayushkevich commented on GitHub (Apr 2, 2025): I attempted to use ollama 0.6.3 and gemma 27b and it works fine. I attempted to use QwQ and here is the result of console commands execution: ``` bash ~$ docker stats --no-stream CONTAINER ID NAME CPU % MEM USAGE / LIMIT MEM % NET I/O BLOCK I/O PIDS 0dd08cb728c4 ollama 0.13% 20.1GiB / 30.46GiB 66.01% 18.2GB / 462MB 41.9GB / 17.9GB 37 ed751f322c16 open-webui 0.10% 67.11MiB / 30.46GiB 0.22% 1.62MB / 6.84MB 660MB / 539MB 39 ~$ docker stop ollama ollama ~$ docker start ollama ollama ~$ docker stats --no-stream CONTAINER ID NAME CPU % MEM USAGE / LIMIT MEM % NET I/O BLOCK I/O PIDS 0dd08cb728c4 ollama 0.00% 18.4MiB / 30.46GiB 0.06% 3.75kB / 126B 53.2kB / 0B 11 ed751f322c16 open-webui 0.08% 67.16MiB / 30.46GiB 0.22% 1.62MB / 6.85MB 660MB / 539MB 39 ~$ free total used free shared buff/cache available Mem: 31935044 16048308 5755192 69300 10662744 15886736 Swap: 8099836 3333888 4765948 ```
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#68662
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?