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 #10118] Maybe propose podman as it works well with GPU too #6638

New Issue
Open
opened 2026-04-12 18:19:15 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 18:19:15 -05:00
Owner
Copy Link

Originally created by @metal3d on GitHub (Apr 3, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10118

I know that Docker is massively used, but Red Hat, Fedora, and many other distributions propose Podman. It provides approximatively the same approach to start ollama and a very nice systemd integration named "Quadlet".

To start ollama with Podman, following the same method to install nvidia-container-kit, we can then launch it in a rootless container:

podman run -d -it --gpus all --security-opts=label=disable -p 11434:11434 docker.io/ollama/ollama

The very nice part is that we can create one of these files:

  • ~/config/containers/systemd/ollama.container for normal user, rootless
  • /etc/container/systemd/ollama.container for root system integration

containing this:

[Container]
ContainerName = "ollama"
Image = "docker.io/ollama/ollama:latest"
PublishPort = "11434:11434"
SecurityLabelDisable=true
Volume = /opt/models:/opt/models:Z
Environment=OLLAMA_MODELS=/opt/models
AddDevice=nvidia.com/gpu=all
AutoUpdate=registry


[Service]
Restart=always

[Install]
WantedBy=default.target

Then, systemctl daemon-reload and systemctl start ollama.
Or for normal users systemctl --user daemon-reload and systemctl --user start ollama

Now, we have ollama in a container, starting with the system, automatically updated, with models in a separated volume, and so on.

Maybe we can add this in the documentation, I think that Podman deserves more visibility as it is installed by default in Rocky, Alma, Fedora, Red Hat...

Originally created by @metal3d on GitHub (Apr 3, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10118 I know that Docker is massively used, but Red Hat, Fedora, and many other distributions propose Podman. It provides approximatively the same approach to start ollama and a very nice systemd integration named "Quadlet". To start ollama with Podman, following the same method to install nvidia-container-kit, we can then launch it in a rootless container: ```bash podman run -d -it --gpus all --security-opts=label=disable -p 11434:11434 docker.io/ollama/ollama ``` The very nice part is that we can create one of these files: - `~/config/containers/systemd/ollama.container` for normal user, rootless - `/etc/container/systemd/ollama.container` for root system integration containing this: ```ini [Container] ContainerName = "ollama" Image = "docker.io/ollama/ollama:latest" PublishPort = "11434:11434" SecurityLabelDisable=true Volume = /opt/models:/opt/models:Z Environment=OLLAMA_MODELS=/opt/models AddDevice=nvidia.com/gpu=all AutoUpdate=registry [Service] Restart=always [Install] WantedBy=default.target ``` Then, `systemctl daemon-reload` and `systemctl start ollama`. Or for normal users `systemctl --user daemon-reload` and `systemctl --user start ollama` Now, we have ollama in a container, starting with the system, automatically updated, with models in a separated volume, and so on. Maybe we can add this in the documentation, I think that Podman deserves more visibility as it is installed by default in Rocky, Alma, Fedora, Red Hat...
GiteaMirror added the feature request label 2026-04-12 18:19:15 -05:00
GiteaMirror commented 2026-04-12 18:19:16 -05:00
Author
Owner
Copy Link

@jbtrystram commented on GitHub (Jun 3, 2025):

You should check ramalama https://github.com/containers/ramalama

<!-- gh-comment-id:2935168391 --> @jbtrystram commented on GitHub (Jun 3, 2025): You should check ramalama https://github.com/containers/ramalama
GiteaMirror commented 2026-04-12 18:19:17 -05:00
Author
Owner
Copy Link

@dikkedimi commented on GitHub (Dec 30, 2025):

this is recommended for bazzite (no way to install docker manually), but it broke and now I'm having trouble finding the guide I followed. I tried installing searxng, but i moved my computer to another room and it stopped working. i have no clue so now I'm trying to see what I might have changed.

<!-- gh-comment-id:3700671478 --> @dikkedimi commented on GitHub (Dec 30, 2025): this is recommended for bazzite (no way to install docker manually), but it broke and now I'm having trouble finding the guide I followed. I tried installing searxng, but i moved my computer to another room and it stopped working. i have no clue so now I'm trying to see what I might have changed.
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
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#6638
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?