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 #11231] ollama continues to run, and cannot kill ollama: "nixos systemd[1]: ollama.service: Failed with result 'oom-kill'." #33158

New Issue
Closed
opened 2026-04-22 15:35:10 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-22 15:35:10 -05:00
Owner
Copy Link

Originally created by @nPrevail on GitHub (Jun 28, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11231

What is the issue?

I was using ollama via WebUI. Left my computer idle for a few minutes. Came back to use WebUI again, and met with an error.

Proceeded to look into server log.

Relevant log output

Server log output:



Jun 28 08:05:25 nixos ollama[1300]: print_info: EOG token        = 151663 '<|repo_name|>'
Jun 28 08:05:25 nixos ollama[1300]: print_info: EOG token        = 151664 '<|file_sep|>'
Jun 28 08:05:25 nixos ollama[1300]: print_info: max token length = 256
Jun 28 08:05:25 nixos ollama[1300]: load_tensors: loading model tensors, this can take a while... (mmap = false)
Jun 28 08:05:25 nixos ollama[1300]: load_tensors:          CPU model buffer size =  4977.62 MiB
Jun 28 08:05:42 nixos ollama[1300]: time=2025-06-28T08:05:42.144-07:00 level=INFO source=server.go:625 msg="waiting for server to become available" status="llm server not responding"
Jun 28 08:05:42 nixos ollama[1300]: time=2025-06-28T08:05:42.146-07:00 level=INFO source=server.go:625 msg="waiting for server to become available" status="llm server not responding"
Jun 28 08:05:42 nixos ollama[1300]: time=2025-06-28T08:05:42.415-07:00 level=INFO source=server.go:625 msg="waiting for server to become available" status="llm server loading model"
Jun 28 08:05:42 nixos ollama[1300]: time=2025-06-28T08:05:42.431-07:00 level=INFO source=server.go:625 msg="waiting for server to become available" status="llm server loading model"
Jun 28 08:05:44 nixos ollama[1300]: time=2025-06-28T08:05:44.448-07:00 level=INFO source=server.go:625 msg="waiting for server to become available" status="llm server not responding"
Jun 28 08:05:44 nixos ollama[1300]: time=2025-06-28T08:05:44.699-07:00 level=INFO source=server.go:625 msg="waiting for server to become available" status="llm server loading model"
Jun 28 08:05:45 nixos ollama[1300]: time=2025-06-28T08:05:45.321-07:00 level=INFO source=ggml.go:556 msg="compute graph" backend=CPU buffer_type=CPU size="287.0 MiB"
Jun 28 08:05:45 nixos ollama[1300]: time=2025-06-28T08:05:45.463-07:00 level=INFO source=server.go:630 msg="llama runner started in 22.42 seconds"
Jun 28 08:05:48 nixos ollama[1300]: time=2025-06-28T08:05:47.388-07:00 level=INFO source=server.go:625 msg="waiting for server to become available" status="llm server not responding"
Jun 28 08:05:53 nixos systemd[1]: ollama.service: A process of this unit has been killed by the OOM killer.
Jun 28 08:05:53 nixos ollama[1300]: [GIN] 2025/06/28 - 08:05:53 | 500 |         3m14s |       127.0.0.1 | POST     "/api/chat"
Jun 28 08:05:53 nixos ollama[1300]: time=2025-06-28T08:05:53.382-07:00 level=WARN source=server.go:598 msg="client connection closed before server finished loading, aborting load"
Jun 28 08:05:53 nixos ollama[1300]: time=2025-06-28T08:05:53.382-07:00 level=ERROR source=sched.go:478 msg="error loading llama server" error="timed out waiting for llama runner to start: context canceled"
Jun 28 08:05:53 nixos ollama[1300]: [GIN] 2025/06/28 - 08:05:53 | 499 | 31.107090248s |       127.0.0.1 | POST     "/api/chat"
Jun 28 08:05:55 nixos systemd[1]: ollama.service: Failed with result 'oom-kill'.
Jun 28 08:05:55 nixos systemd[1]: ollama.service: Consumed 1h 47min 12.316s CPU time, 10.6G memory peak, 4.3G memory swap peak, 52.1G read from disk, 9.6G written to disk, 753.4K incoming IP traffic, 994.6K outgoing IP traffic.

OS

Linux

GPU

Intel

CPU

Intel

Ollama version

0.7.0

Originally created by @nPrevail on GitHub (Jun 28, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11231 ### What is the issue? I was using ollama via WebUI. Left my computer idle for a few minutes. Came back to use WebUI again, and met with an error. Proceeded to look into server log. ### Relevant log output ```shell Server log output: Jun 28 08:05:25 nixos ollama[1300]: print_info: EOG token = 151663 '<|repo_name|>' Jun 28 08:05:25 nixos ollama[1300]: print_info: EOG token = 151664 '<|file_sep|>' Jun 28 08:05:25 nixos ollama[1300]: print_info: max token length = 256 Jun 28 08:05:25 nixos ollama[1300]: load_tensors: loading model tensors, this can take a while... (mmap = false) Jun 28 08:05:25 nixos ollama[1300]: load_tensors: CPU model buffer size = 4977.62 MiB Jun 28 08:05:42 nixos ollama[1300]: time=2025-06-28T08:05:42.144-07:00 level=INFO source=server.go:625 msg="waiting for server to become available" status="llm server not responding" Jun 28 08:05:42 nixos ollama[1300]: time=2025-06-28T08:05:42.146-07:00 level=INFO source=server.go:625 msg="waiting for server to become available" status="llm server not responding" Jun 28 08:05:42 nixos ollama[1300]: time=2025-06-28T08:05:42.415-07:00 level=INFO source=server.go:625 msg="waiting for server to become available" status="llm server loading model" Jun 28 08:05:42 nixos ollama[1300]: time=2025-06-28T08:05:42.431-07:00 level=INFO source=server.go:625 msg="waiting for server to become available" status="llm server loading model" Jun 28 08:05:44 nixos ollama[1300]: time=2025-06-28T08:05:44.448-07:00 level=INFO source=server.go:625 msg="waiting for server to become available" status="llm server not responding" Jun 28 08:05:44 nixos ollama[1300]: time=2025-06-28T08:05:44.699-07:00 level=INFO source=server.go:625 msg="waiting for server to become available" status="llm server loading model" Jun 28 08:05:45 nixos ollama[1300]: time=2025-06-28T08:05:45.321-07:00 level=INFO source=ggml.go:556 msg="compute graph" backend=CPU buffer_type=CPU size="287.0 MiB" Jun 28 08:05:45 nixos ollama[1300]: time=2025-06-28T08:05:45.463-07:00 level=INFO source=server.go:630 msg="llama runner started in 22.42 seconds" Jun 28 08:05:48 nixos ollama[1300]: time=2025-06-28T08:05:47.388-07:00 level=INFO source=server.go:625 msg="waiting for server to become available" status="llm server not responding" Jun 28 08:05:53 nixos systemd[1]: ollama.service: A process of this unit has been killed by the OOM killer. Jun 28 08:05:53 nixos ollama[1300]: [GIN] 2025/06/28 - 08:05:53 | 500 | 3m14s | 127.0.0.1 | POST "/api/chat" Jun 28 08:05:53 nixos ollama[1300]: time=2025-06-28T08:05:53.382-07:00 level=WARN source=server.go:598 msg="client connection closed before server finished loading, aborting load" Jun 28 08:05:53 nixos ollama[1300]: time=2025-06-28T08:05:53.382-07:00 level=ERROR source=sched.go:478 msg="error loading llama server" error="timed out waiting for llama runner to start: context canceled" Jun 28 08:05:53 nixos ollama[1300]: [GIN] 2025/06/28 - 08:05:53 | 499 | 31.107090248s | 127.0.0.1 | POST "/api/chat" Jun 28 08:05:55 nixos systemd[1]: ollama.service: Failed with result 'oom-kill'. Jun 28 08:05:55 nixos systemd[1]: ollama.service: Consumed 1h 47min 12.316s CPU time, 10.6G memory peak, 4.3G memory swap peak, 52.1G read from disk, 9.6G written to disk, 753.4K incoming IP traffic, 994.6K outgoing IP traffic. ``` ### OS Linux ### GPU Intel ### CPU Intel ### Ollama version 0.7.0
GiteaMirror added the bug label 2026-04-22 15:35:10 -05:00
GiteaMirror commented 2026-04-22 15:35:11 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jun 28, 2025):

The kernel killed the ollama runner because it got too big. Try upgrading, there have been fixes for memory leaks (eg #10688).

<!-- gh-comment-id:3015879782 --> @rick-github commented on GitHub (Jun 28, 2025): The kernel killed the ollama runner because it got too big. Try upgrading, there have been fixes for memory leaks (eg #10688).
GiteaMirror commented 2026-04-22 15:35:12 -05:00
Author
Owner
Copy Link

@nPrevail commented on GitHub (Jun 29, 2025):

The kernel killed the ollama runner because it got too big. Try upgrading, there have been fixes for memory leaks (eg #10688).

Should I upgrade the kernel or ollama?

My kernel is currently at 6.14.11.
I'm using NixOS stable. I think on unstable, I can get ollama 0.9.3.

<!-- gh-comment-id:3016750121 --> @nPrevail commented on GitHub (Jun 29, 2025): > The kernel killed the ollama runner because it got too big. Try upgrading, there have been fixes for memory leaks (eg [#10688](https://github.com/ollama/ollama/issues/10688)). Should I upgrade the kernel or ollama? My kernel is currently at 6.14.11. I'm using NixOS stable. I think on unstable, I can get ollama 0.9.3.
GiteaMirror commented 2026-04-22 15:35:13 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jun 29, 2025):

Upgrade ollama.

<!-- gh-comment-id:3016767502 --> @rick-github commented on GitHub (Jun 29, 2025): Upgrade ollama.
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#33158
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?