github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 05:05:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #7077] ollama models cannot be started by systemd #82173

New Issue
Closed
opened 2026-05-09 13:25:07 -05:00 by GiteaMirror · 8 comments
GiteaMirror commented 2026-05-09 13:25:07 -05:00
Owner
Copy Link

Originally created by @kmorber on GitHub (Oct 2, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7077

What is the issue?

ollama models cannot be started by systemd

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.3.12

Originally created by @kmorber on GitHub (Oct 2, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7077 ### What is the issue? ollama models cannot be started by systemd ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.3.12
GiteaMirror added the questionlinux labels 2026-05-09 13:25:07 -05:00
GiteaMirror commented 2026-05-09 13:25:11 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 2, 2024):

Server logs will aid in debugging.

<!-- gh-comment-id:2388044564 --> @rick-github commented on GitHub (Oct 2, 2024): [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) will aid in debugging.
GiteaMirror commented 2026-05-09 13:25:12 -05:00
Author
Owner
Copy Link

@kmorber commented on GitHub (Oct 2, 2024):

Hello,

where can i find the logs in linux?

<!-- gh-comment-id:2388110074 --> @kmorber commented on GitHub (Oct 2, 2024): Hello, where can i find the logs in linux?
GiteaMirror commented 2026-05-09 13:25:14 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 2, 2024):

See here.

<!-- gh-comment-id:2388122055 --> @rick-github commented on GitHub (Oct 2, 2024): [See here](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues).
GiteaMirror commented 2026-05-09 13:25:15 -05:00
Author
Owner
Copy Link

@kmorber commented on GitHub (Oct 2, 2024):

● ollama3.service - ollama3
Loaded: loaded (/usr/lib/systemd/system/ollama3.service; enabled; vendor preset: disabled)
Active: failed (Result: exit-code) since Wed 2024-10-02 11:22:18 CEST; 24min ago
Main PID: 536622 (code=exited, status=2)

Okt 02 11:22:18 morber.net ollama[536622]: github.com/ollama/ollama/envconfig.Models()
Okt 02 11:22:18 morber.net ollama[536622]: github.com/ollama/ollama/envconfig/config.go:89 +0xa9
Okt 02 11:22:18 morber.net ollama[536622]: github.com/ollama/ollama/envconfig.AsMap()
Okt 02 11:22:18 morber.net ollama[536622]: github.com/ollama/ollama/envconfig/config.go:241 +0x713
Okt 02 11:22:18 morber.net ollama[536622]: github.com/ollama/ollama/cmd.NewCLI()
Okt 02 11:22:18 morber.net ollama[536622]: github.com/ollama/ollama/cmd/cmd.go:1406 +0xc11
Okt 02 11:22:18 morber.net ollama[536622]: main.main()
Okt 02 11:22:18 morber.net ollama[536622]: github.com/ollama/ollama/main.go:12 +0x13
Okt 02 11:22:18 morber.net systemd[1]: ollama3.service: Main process exited, code=exited, status=2/INVALIDARGUMENT
Okt 02 11:22:18 morber.net systemd[1]: ollama3.service: Failed with result 'exit-code'.

logs have been uploaded
ollama.log

<!-- gh-comment-id:2388131116 --> @kmorber commented on GitHub (Oct 2, 2024): ● ollama3.service - ollama3 Loaded: loaded (/usr/lib/systemd/system/ollama3.service; enabled; vendor preset: disabled) Active: failed (Result: exit-code) since Wed 2024-10-02 11:22:18 CEST; 24min ago Main PID: 536622 (code=exited, status=2) Okt 02 11:22:18 morber.net ollama[536622]: github.com/ollama/ollama/envconfig.Models() Okt 02 11:22:18 morber.net ollama[536622]: github.com/ollama/ollama/envconfig/config.go:89 +0xa9 Okt 02 11:22:18 morber.net ollama[536622]: github.com/ollama/ollama/envconfig.AsMap() Okt 02 11:22:18 morber.net ollama[536622]: github.com/ollama/ollama/envconfig/config.go:241 +0x713 Okt 02 11:22:18 morber.net ollama[536622]: github.com/ollama/ollama/cmd.NewCLI() Okt 02 11:22:18 morber.net ollama[536622]: github.com/ollama/ollama/cmd/cmd.go:1406 +0xc11 Okt 02 11:22:18 morber.net ollama[536622]: main.main() Okt 02 11:22:18 morber.net ollama[536622]: github.com/ollama/ollama/main.go:12 +0x13 Okt 02 11:22:18 morber.net systemd[1]: ollama3.service: Main process exited, code=exited, status=2/INVALIDARGUMENT Okt 02 11:22:18 morber.net systemd[1]: ollama3.service: Failed with result 'exit-code'. logs have been uploaded [ollama.log](https://github.com/user-attachments/files/17227617/ollama.log)
GiteaMirror commented 2026-05-09 13:25:17 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 2, 2024):

What's the output of:

systemctl cat ollama  --no-pager
systemctl cat ollama1 --no-pager
systemctl cat ollama2 --no-pager
systemctl cat ollama3 --no-pager
journalctl -u ollama  --no-pager
journalctl -u ollama1 --no-pager
journalctl -u ollama2 --no-pager
journalctl -u ollama3 --no-pager
<!-- gh-comment-id:2388423588 --> @rick-github commented on GitHub (Oct 2, 2024): What's the output of: ``` systemctl cat ollama --no-pager systemctl cat ollama1 --no-pager systemctl cat ollama2 --no-pager systemctl cat ollama3 --no-pager journalctl -u ollama --no-pager journalctl -u ollama1 --no-pager journalctl -u ollama2 --no-pager journalctl -u ollama3 --no-pager ```
GiteaMirror commented 2026-05-09 13:25:17 -05:00
Author
Owner
Copy Link

@kmorber commented on GitHub (Oct 2, 2024):

ollama.log

<!-- gh-comment-id:2388488086 --> @kmorber commented on GitHub (Oct 2, 2024): [ollama.log](https://github.com/user-attachments/files/17229020/ollama.log)
GiteaMirror commented 2026-05-09 13:25:18 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 2, 2024):

This is not the way to run multiple models. You need one service, ollama.service. Remove all the others. When you need a model, you load it with the client. If you want the model to stay loaded, set OLLAMA_KEEP_ALIVE=-1 in the server environment. If you want to have 4 models loaded at the same time, set OLLAMA_MAX_LOADED_MODELS=4 in the server environment. If you want to preload models, add this to the ollama.service file:

ExecStartPost=sh -c "for i in mistral wizardlm2 llama3.2 ; do ollama run $i '' ; done"
<!-- gh-comment-id:2388612113 --> @rick-github commented on GitHub (Oct 2, 2024): This is not the way to run multiple models. You need one service, `ollama.service`. Remove all the others. When you need a model, you load it with the client. If you want the model to stay loaded, set `OLLAMA_KEEP_ALIVE=-1` in the server environment. If you want to have 4 models loaded at the same time, set `OLLAMA_MAX_LOADED_MODELS=4` in the server environment. If you want to preload models, add this to the ollama.service file: ``` ExecStartPost=sh -c "for i in mistral wizardlm2 llama3.2 ; do ollama run $i '' ; done" ```
GiteaMirror commented 2026-05-09 13:25:18 -05:00
Author
Owner
Copy Link

@kmorber commented on GitHub (Oct 2, 2024):

Perfect, thanks so much

<!-- gh-comment-id:2388630654 --> @kmorber commented on GitHub (Oct 2, 2024): Perfect, thanks so much
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 linux question
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#82173
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?