github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 08:59:13 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #1601] Error: 403 on pulling manifest #62923

New Issue
Closed
opened 2026-05-03 10:50:06 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-05-03 10:50:06 -05:00
Owner
Copy Link

Originally created by @honggyukim on GitHub (Dec 19, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1601

Hi,

Thanks very much for building this great project!

I would like to set up ollama in the internal Linux server of my office but it fails pulling pre-trained models as follows.

# installation
$ curl https://ollama.ai/install.sh | sh 

# run
$ ollama run llama2 
pulling manifest 
Error: 403:

I've tested it before and it was fine in my home, but it only fails in the office internal server maybe due to security policy.

Could anyone please let me know where ollama downloads the pre-trained models? I need to know its URL to make a firewall exception.

Thanks.

Originally created by @honggyukim on GitHub (Dec 19, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1601 Hi, Thanks very much for building this great project! I would like to set up ollama in the internal Linux server of my office but it fails pulling pre-trained models as follows. ``` # installation $ curl https://ollama.ai/install.sh | sh # run $ ollama run llama2 pulling manifest Error: 403: ``` I've tested it before and it was fine in my home, but it only fails in the office internal server maybe due to security policy. Could anyone please let me know where ollama downloads the pre-trained models? I need to know its URL to make a firewall exception. Thanks.
GiteaMirror commented 2026-05-03 10:50:08 -05:00
Author
Owner
Copy Link

@honggyukim commented on GitHub (Dec 19, 2023):

Otherwise, is there any way manually download the models?

If possible, then I can put the models under /usr/share/ollama/.ollama/models manually.

<!-- gh-comment-id:1862286892 --> @honggyukim commented on GitHub (Dec 19, 2023): Otherwise, is there any way manually download the models? If possible, then I can put the models under `/usr/share/ollama/.ollama/models` manually.
GiteaMirror commented 2026-05-03 10:50:09 -05:00
Author
Owner
Copy Link

@ghost commented on GitHub (Dec 19, 2023):

I have the same problem (also trying to deploy in the office). We have a proxy installed. Does ollama use proxy settings when downloading a model?

<!-- gh-comment-id:1862349984 --> @ghost commented on GitHub (Dec 19, 2023): I have the same problem (also trying to deploy in the office). We have a proxy installed. Does ollama use proxy settings when downloading a model?
GiteaMirror commented 2026-05-03 10:50:09 -05:00
Author
Owner
Copy Link

@mxyng commented on GitHub (Dec 19, 2023):

Ollama uses your system proxy settings if they're set. See the FAQ for more details

<!-- gh-comment-id:1863192442 --> @mxyng commented on GitHub (Dec 19, 2023): Ollama uses your system proxy settings if they're set. See the [FAQ](https://github.com/jmorganca/ollama/blob/main/docs/faq.md#how-do-i-use-ollama-behind-a-proxy) for more details
GiteaMirror commented 2026-05-03 10:50:11 -05:00
Author
Owner
Copy Link

@honggyukim commented on GitHub (Dec 19, 2023):

Thanks for the reply but I haven't configured HTTP_PROXY nor HTTPS_PROXY.

My question is this. Where does ollama download pre-trained models such as llama2?

<!-- gh-comment-id:1863457714 --> @honggyukim commented on GitHub (Dec 19, 2023): Thanks for the reply but I haven't configured `HTTP_PROXY` nor `HTTPS_PROXY`. My question is this. Where does ollama download pre-trained models such as llama2?
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
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#62923
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?