# How to use Hugging Face: find, check and download open models

> Hugging Face is a website and company that hosts open AI models, datasets and demo apps, called Spaces, as git repositories. You search it by task, read a model's card and license, then download its files in a browser or with the `hf` command line tool. A free account covers the basics, and a PRO plan raises the limits.

Mindket editors · Published 2026-11-06 · Updated 2026-11-06 · https://mindket.com/learn/tools/hugging-face

## In short

- The Hub lists more than 2M models, so a task filter and then a license check come before any download.
- Public models download without a token, while gated ones need an account and the authors' approval.
- `hf download` fetches single files, and `--dry-run` previews a download before anything is written.
- The Hub hosts the files. Running a model takes another tool, such as Transformers, Ollama or a hosted provider.

## What Hugging Face is

Hugging Face is a company, and huggingface.co is its website, the Hub, where people share open AI models, datasets and demo apps. Everything on the Hub lives in a repository, a version-controlled folder with commits and branches, much like a GitHub repository. [The Hub documentation](https://huggingface.co/docs/hub/index) puts the count at more than 2M models, 1.5M datasets and 1.5M Spaces, its name for hosted demo apps.

You use it in a browser, from Python with the `huggingface_hub` library, or from a terminal with its `hf` command. Browsing and downloading public models is free with an account or without one. A PRO plan raises your rate limits and adds monthly credits for hosted models, and some features, such as hosting a Gradio demo, need a paid plan.

## What Hugging Face is good for

- **Finding an open model for a job**: pick a task such as text generation on the models page, then narrow by license.
- **Checking whether you may use it**: every model page has a model card, and [its license badge](https://huggingface.co/docs/hub/repositories-licenses) names the license before you build on it.
- **Downloading model files**: `hf download` fetches a whole repository or only the config and weights your code reads, as [the download guide](https://huggingface.co/docs/huggingface_hub/guides/download) shows.
- **Running a model in Python**: the Transformers `pipeline()` call [loads a model from the Hub](https://huggingface.co/docs/transformers/pipeline_tutorial) and runs it in one line.
- **Calling models too big for your computer**: [Inference Providers](https://huggingface.co/docs/inference-providers/index) lets one access token reach several hosted providers.
- **Sharing a small demo**: a Gradio app hosted on a [Space](https://huggingface.co/docs/hub/spaces-overview) gets a public web address.
- **Publishing your own model**: one command, `hf upload`, sends a model folder to your own repository.

## When to use Hugging Face, and when to pick another tool

Reach for Hugging Face when you want the files, the license or the code behind an open model. For a finished assistant to talk to, go straight to a chat product.

| Your job | Use Hugging Face? | Or try |
| --- | --- | --- |
| Find an open model and check its license | Yes, that is what the Hub is for | Ollama's model library, if you only want models that run in Ollama |
| Chat with an assistant or draft a document | No, there is nothing to chat with | ChatGPT, Claude or Gemini |
| Run an open model on your own computer | It supplies the files, and another tool runs them | Ollama or LM Studio |
| Call an open model from code without a GPU of your own | Yes, through Inference Providers | Ollama, for models small enough to run at home |
| Put a small model demo on a web page | Yes, with a Gradio app on a Space | Not needed if the demo stays on your machine |
| Connect apps and automate steps with no code | No | n8n or Zapier |

## How to use Hugging Face, step by step

These six steps need no account. They go from the models list to a gated model, with one screenshot of the site for each.

1. Open [huggingface.co/models](https://huggingface.co/models). Under **Tasks**, click **Text Generation**, then open **Sort** and pick **Most downloads**. The list narrows to text generation models, the most downloaded first.
   ![The Hugging Face models page with the Text Generation task and the Sort: Most downloads button ringed in gold. The list starts with openai-community/gpt2.](https://mindket.com/blog/screens/hugging-face-hub-1-models-page.webp?v=06434f7bd913)
2. Type `gpt2` in the search box at the top. A menu of matches drops down with `openai-community/gpt2` first. Click it.
   ![The search box at the top of the page, ringed in gold, with gpt2 typed in. The menu under it lists models, with openai-community/gpt2 highlighted first.](https://mindket.com/blog/screens/hugging-face-hub-2-search-box.webp?v=d28f4af7c2d1)
3. The page that opens is the model card. The tags under the model name show its task, the libraries that load it and its license. Look for the **License** badge before you build on any model. This one says `mit`.
   ![The openai-community/gpt2 model page. The License: mit badge, among the tags under the model name, is ringed in gold.](https://mindket.com/blog/screens/hugging-face-hub-3-model-card.webp?v=d90ce0cc1b40)
4. Click **Files and versions** (just **Files** in a narrow window), next to **Model card**. This is the repository itself: `config.json` is 665 bytes of settings, and `model.safetensors` holds the weights at 548 MB.
   ![The Files tab of openai-community/gpt2, ringed in gold, above the repository file list, which includes config.json, model.safetensors and pytorch_model.bin.](https://mindket.com/blog/screens/hugging-face-hub-4-files-tab.webp?v=70a8f6b79682)
5. Go back to **Model card** and click **Use this model**. Its menu offers **Transformers** under Libraries, notebooks on Google Colab and Kaggle, and local apps such as vLLM.
   ![The Use this model button on the gpt2 page, ringed in gold, with its menu open: Transformers, Google Colab, Kaggle, vLLM, SGLang and Docker Model Runner.](https://mindket.com/blog/screens/hugging-face-hub-5-use-this-model.webp?v=cb7380141bda)
6. Some models ask for your agreement before they open their files. Open [google/gemma-2-2b](https://huggingface.co/google/gemma-2-2b) while signed out. A box says you must accept the conditions to reach the files, and it ends in **Log in** and **Sign Up** buttons.
   ![The google/gemma-2-2b model page. The Access Gemma on Hugging Face box, ringed in gold, says to accept the conditions and has Log in and Sign Up buttons.](https://mindket.com/blog/screens/hugging-face-hub-6-gated-model.webp?v=6d7fe7c0a76e)

*Screenshots of huggingface.co, taken on 6 November 2026.*

> The tutorials at the top of this page show these steps on screen. Signing in, making an access token and downloading with the hf command are covered in lesson 1.

## An example to try

These two lines install the library and preview what downloading GPT-2 would fetch. A dry run writes nothing, and a public model needs no token, so it is safe to try first. [The download guide](https://huggingface.co/docs/huggingface_hub/guides/download) describes the flag.

````bash
pip install -U "huggingface_hub"
hf download openai-community/gpt2 --dry-run
````

- The output lists the files in the repository and the bytes each would add. Nothing lands on your disk.
- In the docs' own example run, the repository held 26 files. Most of the size was the same model saved again for other tools, and your run may list other numbers.
- Add the file names you want, as in `hf download gpt2 config.json model.safetensors`, to fetch only those.

## Tips for better results

- Filter by task first and by license second, then open the model card. [The model card docs](https://huggingface.co/docs/hub/model-cards) explain the keys behind the badges.
- When a repository holds the same weights in several formats, download the `safetensors` copy. The Transformers docs call the older `.bin` files insecure.
- Use [the CLI guide](https://huggingface.co/docs/huggingface_hub/guides/cli) commands to clean up: `hf cache ls` lists what is stored and `hf cache rm` deletes what you name.
- Make one [access token](https://huggingface.co/settings/tokens) per machine or app, so revoking one leaves the rest working.
- Old tutorials say `huggingface-cli login`. [The v1.0 migration guide](https://huggingface.co/docs/huggingface_hub/concepts/migration) lists that name as removed, and the command is now `hf auth login`.

## Limits to know

- Signed-out requests get the lowest [rate limits](https://huggingface.co/docs/hub/rate-limits), counted per IP address in 5-minute windows. Past the limit the Hub answers with error 429, and a missing token is the usual cause.
- A [gated model](https://huggingface.co/docs/hub/models-gated) opens only after its authors approve a request, and they can withdraw access later. Note an open alternative before you build on one.
- A license badge names the license and cannot say whether your use fits. Read the terms before a model goes into a product you sell.
- Hosting a Gradio demo on a Space is not free for everyone. The Spaces lesson shows which plan it needs.

## YouTube tutorials

- [What is Hugging Face? - Models, Datasets & Spaces](https://www.youtube.com/watch?v=qP9mbY3wuWk) (Hugging Face)
- [Hugging Face Tutorial for Beginners](https://www.youtube.com/watch?v=3xLTD5wSBEs) (Prof. Ryan Ahmed)
- [What Is Hugging Face and How To Use It](https://www.youtube.com/watch?v=3kRB2TXewus) (Angel Poon)
- [Deploying AI Models with Hugging Face – Hands-On Course](https://www.youtube.com/watch?v=R8h_gpSpEVU) (freeCodeCamp.org)

## Learn more about Hugging Face

- [Hugging Face tutorial: find, check and download open models](https://mindket.com/learn/hugging-face/hugging-face-hub)
- [Transformers pipeline: run open models in Python, on CPU or GPU](https://mindket.com/learn/hugging-face/transformers-pipeline)
- [Hugging Face Inference API: call hosted open models with Inference Providers](https://mindket.com/learn/hugging-face/hugging-face-inference-providers)
- [Hugging Face Spaces and Gradio tutorial: build a demo and host it](https://mindket.com/learn/hugging-face/gradio-spaces)

## Frequently asked questions

### Is Hugging Face free?

Yes for the basics. An account, browsing and downloading public models cost nothing. A PRO plan raises your rate limits and adds monthly credits for hosted models, while free accounts get no monthly credits but can buy some.

### Do I need an account to download a model?

Not for a public model. Gated models need an account and the authors' approval, and signed-out downloads get the lowest rate limits. A free account with an access token lifts those limits and is the better default for any script.

### What is a model card?

It is the README of a model repository, shown at the top of the model page. A block of metadata at its start feeds the license badge, the task tag and the filters, and the text below says what the model is for and how to use it.

### What is a gated model?

A model whose authors want a request before the files open. You agree to their conditions while signed in, and with automatic approval the files open at once. With manual approval you wait, and the authors can block your access later.

### How do I download a model from Hugging Face?

Click **Files and versions** on the model page to download single files in the browser, or run `hf download` with the repository name. Add file names to fetch only those, and `--dry-run` to preview first.

### Can I use a Hugging Face model in a product I sell?

It depends on the license on its card. Licenses such as `apache-2.0` and `mit` are permissive, `cc-by-nc-4.0` forbids commercial use and `license: other` points to custom terms you must read.

### What is the difference between Hugging Face and Ollama?

Hugging Face hosts model files and the code to load them. Ollama downloads models and runs them on your computer, and it can pull GGUF repositories from the Hub with `ollama run hf.co/{username}/{repository}`.

## Sources

- [Hugging Face Hub documentation](https://huggingface.co/docs/hub/index) (read 2026-11-05)
- [Hugging Face Hub: Model cards](https://huggingface.co/docs/hub/model-cards) (read 2026-11-05)
- [Hugging Face Hub: Licenses](https://huggingface.co/docs/hub/repositories-licenses) (read 2026-11-05)
- [Hugging Face Hub: Gated models](https://huggingface.co/docs/hub/models-gated) (read 2026-11-05)
- [Hugging Face Hub: User access tokens](https://huggingface.co/docs/hub/security-tokens) (read 2026-11-05)
- [Hugging Face Hub: Rate limits](https://huggingface.co/docs/hub/rate-limits) (read 2026-11-05)
- [huggingface_hub: Command Line Interface (CLI)](https://huggingface.co/docs/huggingface_hub/guides/cli) (read 2026-11-05)
- [Hugging Face: Download files from the Hub](https://huggingface.co/docs/huggingface_hub/guides/download) (read 2026-11-05)
- [huggingface_hub: Migrating to v1.0](https://huggingface.co/docs/huggingface_hub/concepts/migration) (read 2026-11-05)
- [Hugging Face Hub: Spaces overview](https://huggingface.co/docs/hub/spaces-overview) (read 2026-11-05)
- [Inference Providers overview](https://huggingface.co/docs/inference-providers/index) (read 2026-11-05)
- [Transformers: Pipeline](https://huggingface.co/docs/transformers/pipeline_tutorial) (read 2026-11-05)

[Start the lesson](https://mindket.com/learn/hugging-face/hugging-face-hub)