github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #7240] Pull Private Huggingface Model #66655

New Issue
Open
opened 2026-05-04 07:44:03 -05:00 by GiteaMirror · 6 comments
GiteaMirror commented 2026-05-04 07:44:03 -05:00
Owner
Copy Link

Originally created by @DaddyCodesAlot on GitHub (Oct 17, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7240

Hi, so I believe it's now possible to pull huggingface models directly by prepending hf.co to the pull statement. I would just like to get clarity on how this works with private models? I have my huggingface token set as an environment variable, but I can't seem to pull a private model.

Originally created by @DaddyCodesAlot on GitHub (Oct 17, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7240 Hi, so I believe it's now possible to pull huggingface models directly by prepending hf.co to the pull statement. I would just like to get clarity on how this works with private models? I have my huggingface token set as an environment variable, but I can't seem to pull a private model.
GiteaMirror added the feature request label 2026-05-04 07:44:03 -05:00
GiteaMirror commented 2026-05-04 07:44:06 -05:00
Author
Owner
Copy Link

@pongib commented on GitHub (Nov 4, 2024):

same problem.

<!-- gh-comment-id:2455074589 --> @pongib commented on GitHub (Nov 4, 2024): same problem.
GiteaMirror commented 2026-05-04 07:44:07 -05:00
Author
Owner
Copy Link

@Inigo-13 commented on GitHub (Nov 22, 2024):

Same problem here for private models!

Launching ollama model 'hf.co/.../...-GGUF'...
pulling manifest 
Error: pull model manifest: Get (...): unsupported protocol scheme ""

I also tried to set a different url using https directly with user/token auth, something like:

https://<user>:<token>@huggingface.co/<site>/<model>-GGUF

But with no luck!

<!-- gh-comment-id:2493592093 --> @Inigo-13 commented on GitHub (Nov 22, 2024): Same problem here for private models! ``` Launching ollama model 'hf.co/.../...-GGUF'... pulling manifest Error: pull model manifest: Get (...): unsupported protocol scheme "" ``` I also tried to set a different url using https directly with user/token auth, something like: ``` https://<user>:<token>@huggingface.co/<site>/<model>-GGUF ``` But with no luck!
GiteaMirror commented 2026-05-04 07:44:10 -05:00
Author
Owner
Copy Link

@spolspol commented on GitHub (Feb 5, 2025):

+1

<!-- gh-comment-id:2638159063 --> @spolspol commented on GitHub (Feb 5, 2025): +1
GiteaMirror commented 2026-05-04 07:44:11 -05:00
Author
Owner
Copy Link

@Inigo-13 commented on GitHub (Feb 6, 2025):

Well, a few days after my comment, the feature was implemented in the huggingface-hub library!
Look here for more details: https://huggingface.co/docs/hub/en/ollama#run-private-ggufs-from-the-hugging-face-hub

<!-- gh-comment-id:2639106061 --> @Inigo-13 commented on GitHub (Feb 6, 2025): Well, a few days after my comment, the feature was implemented in the huggingface-hub library! Look here for more details: https://huggingface.co/docs/hub/en/ollama#run-private-ggufs-from-the-hugging-face-hub
GiteaMirror commented 2026-05-04 07:44:12 -05:00
Author
Owner
Copy Link

@joe-speedboat commented on GitHub (Jan 17, 2026):

@Inigo-13
I hit rate limit even if i followed the guide you mentioned.
I assumed that authenticated user are visible at huggingface, but maybe its different.
Does anyone know some details about this issue or having the same problem?

Thanks
Chris

ollama@spark:# ollama run hf.co/unsloth/Qwen3-Next-80B-A3B-Instruct-GGUF:Q4_K_M
pulling manifest 
Error: pull model manifest: 429: {"error":"We had to rate limit your IP (1.1.1.1). To continue using our service, create a HF account or login to your existing account, and make sure you pass a HF_TOKEN if you're using the API."

ollama@spark:~# ollama -v
ollama version is 0.14.2
<!-- gh-comment-id:3764114508 --> @joe-speedboat commented on GitHub (Jan 17, 2026): @Inigo-13 I hit rate limit even if i followed the guide you mentioned. I assumed that authenticated user are visible at huggingface, but maybe its different. Does anyone know some details about this issue or having the same problem? Thanks Chris ``` ollama@spark:# ollama run hf.co/unsloth/Qwen3-Next-80B-A3B-Instruct-GGUF:Q4_K_M pulling manifest Error: pull model manifest: 429: {"error":"We had to rate limit your IP (1.1.1.1). To continue using our service, create a HF account or login to your existing account, and make sure you pass a HF_TOKEN if you're using the API." ollama@spark:~# ollama -v ollama version is 0.14.2 ```
GiteaMirror commented 2026-05-04 07:44:14 -05:00
Author
Owner
Copy Link

@rlutsch18 commented on GitHub (Jan 18, 2026):

Same at me.
a few weeks ago no problems pulling huggingface models.

ollama pull hf.co/bartowski/nvidia_NVIDIA-Nemotron-Nano-12B-v2-GGUF:Q8_0
pulling manifest
Error: pull model manifest: 429: {"error":"We had to rate limit your IP (10.0.182.203). To continue using our service, create a HF account or login to your existing account, and make sure you pass a HF_TOKEN if you're using the API."}

ollama -v
ollama version is 0.14.2

Thanks!
Richi

<!-- gh-comment-id:3765210825 --> @rlutsch18 commented on GitHub (Jan 18, 2026): Same at me. a few weeks ago no problems pulling huggingface models. ollama pull hf.co/bartowski/nvidia_NVIDIA-Nemotron-Nano-12B-v2-GGUF:Q8_0 pulling manifest Error: pull model manifest: 429: {"error":"We had to rate limit your IP (10.0.182.203). To continue using our service, create a HF account or login to your existing account, and make sure you pass a HF_TOKEN if you're using the API."} ollama -v ollama version is 0.14.2 Thanks! Richi
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#66655
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?