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 #5489] Running Hugging Face Models #3434

New Issue
Closed
opened 2026-04-12 14:05:33 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 14:05:33 -05:00
Owner
Copy Link

Originally created by @theainerd on GitHub (Jul 4, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5489

Hi team,

Can we load Hugging Face models directly using ollama?

Originally created by @theainerd on GitHub (Jul 4, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5489 Hi team, Can we load Hugging Face models directly using ollama?
GiteaMirror added the feature request label 2026-04-12 14:05:33 -05:00
GiteaMirror commented 2026-04-12 14:05:35 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Jul 8, 2024):

@theainerd do you mean something like being able to run ollama run https://huggingface.co/path/to/model or do you mean being able to import models from HF Safetensors?

For the first use case, it's really hard to do that because we don't support many of the models which are available on HF which results in a broken user experience. This is the case for llama.cpp right now. For the second use case, we actually do support converting many models from Safetensors, including Llama2/Llama3, Gemma, and Mistral/Mixtral based models. If you include the path in the FROM line of a model file, you can use ollama create to directly import the models into Ollama.

I'm going to go ahead and close the issue, but feel free to keep commenting. If I misunderstood something we can reopen.

<!-- gh-comment-id:2215473332 --> @pdevine commented on GitHub (Jul 8, 2024): @theainerd do you mean something like being able to run `ollama run https://huggingface.co/path/to/model` or do you mean being able to import models from HF Safetensors? For the first use case, it's really hard to do that because we don't support many of the models which are available on HF which results in a broken user experience. This is the case for llama.cpp right now. For the second use case, we actually do support converting many models from Safetensors, including Llama2/Llama3, Gemma, and Mistral/Mixtral based models. If you include the path in the `FROM` line of a model file, you can use `ollama create` to directly import the models into Ollama. I'm going to go ahead and close the issue, but feel free to keep commenting. If I misunderstood something we can reopen.
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#3434
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?