github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #11052] Deploy a model by manul #33050

New Issue
Closed
opened 2026-04-22 15:14:21 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-22 15:14:21 -05:00
Owner
Copy Link

Originally created by @fishfl on GitHub (Jun 12, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11052

What is the issue?

So we have a stage environment and a production environment.
The production environment can't access the public internet. So we can't pull a model from your library, like: ollama pull llama3.2, it's not work.

But we can access the WLAN and download model files from a Local storage like HDFS.

So whether can we run
‘ollama pull llama3.2’ in a stage environment to download the models files and then upload the model files to our Local storage.
And in a production environment, we download model files from the Local storage,
Then move the files to a host path like '/root/.ollama/models/' or somewhere.

Is that work for ollama? Can ollama identify the model from the host files instead of pull it from your library?

Thanks very much!

Relevant log output

OS

Linux

GPU

No response

CPU

Intel

Ollama version

0.9.1

Originally created by @fishfl on GitHub (Jun 12, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11052 ### What is the issue? So we have a stage environment and a production environment. The production environment can't access the public internet. So we can't pull a model from your library, like: ollama pull llama3.2, it's not work.  But we can access the WLAN and download model files from a Local storage like HDFS.  So whether can we run ‘ollama pull llama3.2’ in a stage environment to download the models files and then upload the model files to our Local storage. And in a production environment, we download model files from the Local storage, Then move the files to a host path like '/root/.ollama/models/' or somewhere.  Is that work for ollama? Can ollama identify the model from the host files instead of pull it from your library?  Thanks very much! ### Relevant log output ```shell ``` ### OS Linux ### GPU _No response_ ### CPU Intel ### Ollama version 0.9.1
GiteaMirror added the question label 2026-04-22 15:14:21 -05:00
GiteaMirror commented 2026-04-22 15:14:31 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jun 12, 2025):

Yes, just copy $OLLAMA_HOME/.ollama/models from staging to local storage, and then to /root/.ollama/models in production.

<!-- gh-comment-id:2965525659 --> @rick-github commented on GitHub (Jun 12, 2025): Yes, just copy `$OLLAMA_HOME/.ollama/models` from staging to local storage, and then to `/root/.ollama/models` in production.
GiteaMirror commented 2026-04-22 15:14:32 -05:00
Author
Owner
Copy Link

@hlstudio commented on GitHub (Jun 13, 2025):

The same as above, in a new Ollama environment, only download ollama pull llama3.2. You can confirm that only the llama3.2 model is present by using ollama list. Then directly copy the current models folder to the production environment's models, ensuring the folder hierarchy corresponds, so that the production environment can add a new llama3.2 large model.

<!-- gh-comment-id:2968744194 --> @hlstudio commented on GitHub (Jun 13, 2025): The same as above, in a new Ollama environment, only download ollama pull llama3.2. You can confirm that only the llama3.2 model is present by using ollama list. Then directly copy the current models folder to the production environment's models, ensuring the folder hierarchy corresponds, so that the production environment can add a new llama3.2 large model.
GiteaMirror commented 2026-04-22 15:14:32 -05:00
Author
Owner
Copy Link

@fishfl commented on GitHub (Jun 13, 2025):

Got it , Thank you very much. It works!

<!-- gh-comment-id:2969655434 --> @fishfl commented on GitHub (Jun 13, 2025): Got it , Thank you very much. It works!
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 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#33050
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?