Zero GPU Spaces

Zero GPU Spaces

Shows a browsable list of Hugging Face Spaces that run on ZeroGPU hardware. It suits people looking for AI demos that use shared GPU time.

Made by enzostvs on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: This Space is a directory page that lists other Hugging Face Spaces using ZeroGPU. It is built as a Next.js web app with Tailwind and packed in a Docker image, and it runs on cpu-basic hardware at Hugging Face.

Who it suits: It suits people who want to find AI demos that run on ZeroGPU, and developers who want to see how such a listing page is built.

Industry | Who uses it | How they use it | Example
AI development | Developers and model authors | Look through Spaces that already use ZeroGPU | Find a similar demo before building their own
Research | Researchers and students | Find runnable demos of new models | Pick a demo to try in the browser
Web development | Front-end developers | Study a Next.js app packed in Docker | Read the app folder and Dockerfile

You can skip it if you only want to run one specific model, since it is a list and does not run a model itself.

Where to use it: You can use it in these places:

• A browser: open the Space's page on Hugging Face and nothing needs installing.
• Windows, macOS or Linux: build and run your own copy with Docker.

Use case | Who | What they get back
Finding ZeroGPU demos | Developers and hobbyists | A list of Spaces that use ZeroGPU
Studying the code | Web developers | A Next.js project with a Dockerfile to read

How to set it up: You need these first for a local copy:

• Python and pip, to download the files
• Docker, to build and run the image

The online page needs none of this. For your own copy, follow the steps below.

1. Install the Hugging Face tools.
2. Download the Space's files into a folder.
3. Move into that folder.
4. Build the Docker image.
5. Run it with port 3000 open.

pip install -U huggingface_hub
hf download enzostvs/zero-gpu-spaces --repo-type space --local-dir zero-gpu-spaces
cd zero-gpu-spaces
docker build -t zero-gpu-spaces .
docker run -it -p 3000:3000 zero-gpu-spaces

How to use it: Open the Space in a browser and scroll through the list of Spaces. With your own copy running, the same page is served on port 3000.

docker run -it -p 3000:3000 zero-gpu-spaces

Tool | What it does
docker build | Builds the image from the Dockerfile
docker run | Starts the app with port 3000 open

Example: You open the Space, look down the list and find a demo that uses ZeroGPU. You open that demo in your browser to try it.

For newcomers and experts: If you are new to this, open the Space page and look through the list. Open one entry that looks interesting and try that demo.

If you know the field, the repository is a Next.js app with Tailwind styling and a Dockerfile, so it runs on the cheapest CPU hardware. The trade-off is that it only lists Spaces and does no GPU work itself.

You open the Space page
The Next.js app serves the list
You pick a ZeroGPU Space
That Space opens on its own page

Good to know: The page is a list of other Spaces, so what you can try depends on those Spaces.

• License: mit
• Cost to run: none named
• Data it reaches: the Hugging Face Spaces it lists
• Not for: running models, since it only lists Spaces

On Hugging Face, 13 November 2026

• Likes: 985
• Built with: docker
• License: mit

Links

• Space: https://huggingface.co/spaces/enzostvs/zero-gpu-spaces
• Files: https://huggingface.co/spaces/enzostvs/zero-gpu-spaces/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.