[GH-ISSUE #11802] push model to local machine #7829

Closed
opened 2026-04-12 20:00:01 -05:00 by GiteaMirror · 1 comment
Owner

Originally created by @pamdla on GitHub (Aug 8, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11802

I have two machines. Machine A has lots of models, but machine B cannot access to internet.
my question is how to push the specific models from A to B ?

Don;t use sync because it will upload all files from A to B.

Originally created by @pamdla on GitHub (Aug 8, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11802 I have two machines. Machine A has lots of models, but machine B cannot access to internet. my question is how to push the specific models from A to B ? Don;t use sync because it will upload all files from A to B.
GiteaMirror added the feature request label 2026-04-12 20:00:01 -05:00
Author
Owner

@rick-github commented on GitHub (Aug 8, 2025):

You can set up a registry and push the model from machine A to the registry, and then pull the model from the registry to machine B.

Alternatively, use a script to parse the manifest on machine A and create an archive of the required model, copy the archive to machine B and extract.

<!-- gh-comment-id:3167861945 --> @rick-github commented on GitHub (Aug 8, 2025): You can set up a [registry](https://hub.docker.com/_/registry) and push the model from machine A to the registry, and then pull the model from the registry to machine B. Alternatively, use a [script](https://github.com/ollama/ollama/issues/6037#issuecomment-2255540441) to parse the manifest on machine A and create an archive of the required model, copy the archive to machine B and extract.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#7829