github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-15 20:54:54 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #11666] Support pull without a running server #69773

New Issue
Open
opened 2026-05-04 19:08:59 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-05-04 19:08:59 -05:00
Owner
Copy Link

Originally created by @ag-TJNII on GitHub (Aug 5, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11666

There are Docker use cases where it's desirable to "bake" the model into a custom Docker image. For example, if a Ollama server container is intended to run with restricted network access for data controls, it is useful to already have the model cached and ready.

There is a convenient pull command for this, but it requires a running server:

$ docker run --rm -ti ollama/ollama pull llama3:8b
Error: ollama server not responding - could not connect to ollama server, run 'ollama serve' to start it

The workaround from https://github.com/ollama/ollama/issues/9888#issuecomment-2736224280 is functional, but not ideal. Take the following Dockerfile:

FROM ollama/ollama

RUN ollama serve & server=$! ; \
    sleep 2 ; \
    ollama pull llama3:8b ; \
    kill $server

This:

  • Starts the server as a background process
  • Sleeps two seconds for the server to start
  • Pulls the model
  • Manually kills the server

Rather than starting two processes in the RUN step, and needing to manage the background process, it would be nice if ollama pull didn't rely on a background server running. This would make pre-caching models easier.

Thank you for considering this feature.

Originally created by @ag-TJNII on GitHub (Aug 5, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11666 There are Docker use cases where it's desirable to "bake" the model into a custom Docker image. For example, if a Ollama server container is intended to run with restricted network access for data controls, it is useful to already have the model cached and ready. There is a convenient `pull` command for this, but it requires a running server: ```bash $ docker run --rm -ti ollama/ollama pull llama3:8b Error: ollama server not responding - could not connect to ollama server, run 'ollama serve' to start it ``` The workaround from https://github.com/ollama/ollama/issues/9888#issuecomment-2736224280 is functional, but not ideal. Take the following Dockerfile: ```Dockerfile FROM ollama/ollama RUN ollama serve & server=$! ; \ sleep 2 ; \ ollama pull llama3:8b ; \ kill $server ``` This: - Starts the server as a background process - Sleeps two seconds for the server to start - Pulls the model - Manually kills the server Rather than starting two processes in the `RUN` step, and needing to manage the background process, it would be nice if `ollama pull` didn't rely on a background server running. This would make pre-caching models easier. Thank you for considering this feature.
GiteaMirror added the feature request label 2026-05-04 19:08:59 -05:00
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#69773
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?