github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 13:19:40 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #6306] Running ollama on island device with no Internet connection #3954

New Issue
Closed
opened 2026-04-12 14:49:46 -05:00 by GiteaMirror · 11 comments
GiteaMirror commented 2026-04-12 14:49:46 -05:00
Owner
Copy Link

Originally created by @whatdhack on GitHub (Aug 11, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6306

Trying to run ollama on island devices with no Internet connection. Getting the following error message.

Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/llama2/manifests/latest":

Originally created by @whatdhack on GitHub (Aug 11, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6306 Trying to run ollama on island devices with no Internet connection. Getting the following error message. `Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/llama2/manifests/latest":`
GiteaMirror added the feature request label 2026-04-12 14:49:46 -05:00
GiteaMirror commented 2026-04-12 14:49:47 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Aug 11, 2024):

Downloading a model requires internet connectivity. You can download the model on a different computer and copy it across if the island device cannot be connected. Where the model is stored depends on your setup.

<!-- gh-comment-id:2282689857 --> @rick-github commented on GitHub (Aug 11, 2024): Downloading a model requires internet connectivity. You can download the model on a different computer and copy it across if the island device cannot be connected. Where the [model is stored](https://github.com/ollama/ollama/blob/main/docs/faq.md#where-are-models-stored) depends on your setup.
GiteaMirror commented 2026-04-12 14:49:48 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Aug 11, 2024):

Hi @whatdhack as @rick-github mentioned you'd need to be connected to ollama pull a model, or to ollama run (if you don't have it yet)

<!-- gh-comment-id:2282833538 --> @jmorganca commented on GitHub (Aug 11, 2024): Hi @whatdhack as @rick-github mentioned you'd need to be connected to `ollama pull` a model, or to `ollama run` (if you don't have it yet)
GiteaMirror commented 2026-04-12 14:49:48 -05:00
Author
Owner
Copy Link

@whatdhack commented on GitHub (Aug 11, 2024):

Can ollama use the Meta format models ? For example the 16GB llama 3.1 models ?

<!-- gh-comment-id:2282850293 --> @whatdhack commented on GitHub (Aug 11, 2024): Can ollama use the Meta format models ? For example the 16GB llama 3.1 models ?
GiteaMirror commented 2026-04-12 14:49:49 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Aug 11, 2024):

https://ollama.com/library/llama3.1

<!-- gh-comment-id:2282850630 --> @rick-github commented on GitHub (Aug 11, 2024): https://ollama.com/library/llama3.1
GiteaMirror commented 2026-04-12 14:49:49 -05:00
Author
Owner
Copy Link

@whatdhack commented on GitHub (Aug 11, 2024):

On a host with access to the Internet, I set the OLLAMA_MODELS variable. It was ignored and ollama pulled the model to ~/.ollama .

<!-- gh-comment-id:2282852247 --> @whatdhack commented on GitHub (Aug 11, 2024): On a host with access to the Internet, I set the OLLAMA_MODELS variable. It was ignored and ollama pulled the model to ~/.ollama .
GiteaMirror commented 2026-04-12 14:49:50 -05:00
Author
Owner
Copy Link

@whatdhack commented on GitHub (Aug 11, 2024):

https://ollama.com/library/llama3.1 shows it is using the 4 bit checkpoint

<!-- gh-comment-id:2282852880 --> @whatdhack commented on GitHub (Aug 11, 2024): https://ollama.com/library/llama3.1 shows it is using the 4 bit checkpoint
GiteaMirror commented 2026-04-12 14:49:50 -05:00
Author
Owner
Copy Link

@whatdhack commented on GitHub (Aug 11, 2024):

Still tries to pull , even when the model was already available in ~/.ollama/models

<!-- gh-comment-id:2282858990 --> @whatdhack commented on GitHub (Aug 11, 2024): Still tries to pull , even when the model was already available in ~/.ollama/models
GiteaMirror commented 2026-04-12 14:49:51 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Aug 11, 2024):

https://ollama.com/library/llama3.1:8b-instruct-fp16

<!-- gh-comment-id:2282859436 --> @rick-github commented on GitHub (Aug 11, 2024): https://ollama.com/library/llama3.1:8b-instruct-fp16
GiteaMirror commented 2026-04-12 14:49:51 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Aug 11, 2024):

The ollama server does the work of pulling the model, so OLLAMA_MODELS has to set in the environment of the server.

<!-- gh-comment-id:2282860769 --> @rick-github commented on GitHub (Aug 11, 2024): The ollama server does the work of pulling the model, so `OLLAMA_MODELS` has to set in the environment of the server.
GiteaMirror commented 2026-04-12 14:49:52 -05:00
Author
Owner
Copy Link

@whatdhack commented on GitHub (Aug 11, 2024):

Hmm, "OLLAMA_MODELS has to set in the environment of the server " - was in fact set

<!-- gh-comment-id:2282862838 --> @whatdhack commented on GitHub (Aug 11, 2024): Hmm, "OLLAMA_MODELS has to set in the environment of the server " - was in fact set
GiteaMirror commented 2026-04-12 14:49:52 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Aug 11, 2024):

Server logs will help in debugging.

<!-- gh-comment-id:2282863587 --> @rick-github commented on GitHub (Aug 11, 2024): [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) will help in debugging.
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#3954
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?