Step By Step Instructions for Working With Large Models via Hugging Face

Managing large model files on Hugging Face can feel cumbersome, especially when dealing with multigigabyte embeddings or generative models. Fortunately, the Hugging Face CLI now streamlines the entire process.

Start reading
Updated
3 min read

Managing large model files on Hugging Face can feel cumbersome — especially when dealing with multigigabyte embeddings or generative models. Fortunately, the Hugging Face CLI provides a straightforward workflow for downloading public models and re-uploading them to your own repositories, including large ones that support resumable uploads.

In this post, we’ll walk through exactly how you can:

  • Download a large model (like Qwen3-Embedding-8B) directly from Hugging Face.
  • Upload it to your own repo (in this case, OpenSite/forge).
  • Handle connection drops, resumable uploads, and commit messages — all from your terminal.

This is a simple, CLI-first guide that gets you productive fast with model management, especially if you’re maintaining open-access or shared AI model repositories.

Step 1 — Download the model #

Assuming you have the hf cli installed on your system

The example below uses the following examples:

bash
hf download Qwen/Qwen3-Embedding-8B --local-dir ./Qwen3-Embedding-8B

This downloads all model files into a Qwen3-Embedding-8B/ subdirectory.

Step 2 — Upload to OpenSite/forge #

Since this is an 8B model (likely 15-30GB), use the large-folder uploader for resumable uploads:

bash
hf upload-large-folder OpenSite/forge ./Qwen3-Embedding-8B

Or if you prefer the standard uploader (non-resumable):

bash
hf upload OpenSite/forge ./Qwen3-Embedding-8B

Notes #

  • The download will take a while — Qwen3-Embedding-8B is ~15GB in bf16 format
  • upload-large-folder is strongly recommended here since it supports resuming if the connection drops mid-upload
  • Both commands will use your currently logged-in HF token automatically
  • If you want to add a commit message to the upload: --commit-message "Add Qwen3-Embedding-8B"

You can verify your login first with:

bash
hf auth whoami

That’s it — two commands and you’re done. With the hf CLI, managing massive model files no longer needs to be painful. Whether you’re curating open-access models like we do at OpenSite AI, or just organizing internal repositories, this workflow keeps things simple, repeatable, and automatable.

👉 Check out our OpenSite/forge Hugging Face repo for open-source models and embeddings, or visit opensite.ai/developers to explore our latest AI infrastructure tools.

Written by

I’m Jordan Hudgens, a technical educator and AI engineering leader. I built the instructor-development system at Bottega University, from required onboarding and teaching observations to clearance standards and ongoing training. Today I lead an eight-person team building production AI at Encapsa and teach customer teams during every deployment.

Published guides
4
Total views
31
Average read
17 min

What did you think?

Discussion

No comments yet

Start the first thread with a question, a tip, or something you learned.