Hugging Face
Hugging Face Spaces
Hugging Face Spaces lets you create and deploy ML-powered demos in minutes. Hugging Face’s documentation covers creating a Space, choosing an SDK, setting visibility and the hardware each Space runs on.
What Hugging Face Spaces does
- Hosts ML demos and apps, each stored in a git repository like models and datasets on the Hub.
- Offers Static, Gradio and Docker Spaces, chosen when you create one.
- Sets visibility to public, protected or private, which changes who can see the code and reach the app.
- Runs each Space on default hardware of 16GB RAM, 2 CPU cores and 50GB of non-persistent disk, with upgrades available.
What people use it for
Show a model
Wrap a model in a small Gradio app so others can try it in a browser.
Share a prototype
Deploy a demo from a git repository and send a link.
Keep a demo private
Use private visibility while you test, then open it up.
Who it suits
- Developers and researchers who want to publish a working demo without running servers.
- Learners who want to see how other people’s ML demos are built, since public Spaces show their source.
Plans and access
Hugging Face says Static Spaces are free for everyone, while Gradio and Docker Spaces run on compute and need a paid plan to create. Free personal accounts in good standing can host up to 2 Gradio Spaces running on ZeroGPU. Protected visibility needs a PRO, Team or Enterprise plan. Plans change, so read the current documentation. Public Spaces expose their source, so never put secrets in the repository.
How to start
- 1Read the Spaces overview. Open
- 2Create a Space and choose an SDK.
- 3Deploy a small example and open its page.
- 4Check the visibility setting before you share the link.
Watch and learn
Videos from Hugging Face’s own channel, so you can learn it here. Nothing loads from YouTube until you press play. More on the Hugging Face channel.
Hugging Face · 2021
Showcase your model demos with 🤗 Spaces
Hugging Face · 2021
Build and Deploy a Machine Learning App in 2 Minutes
Hugging Face · 2022
A Tour Through The Hugging Face Hub & A Hands on Guide To Gradio
Keep learning on Infrato
- Course: AI for Everyone
- Path: AI for software developers
- Directory: 13 courses from Hugging Face
- More tools for learning and study
Similar tools
Google AI StudioGoogleBuild with Gemini, from prompt to production.
GuideCoding and buildingaistudio.google.com19 courses
Common questions about Hugging Face Spaces
- What is a Hugging Face Space?
- A Space is a hosted app or demo, stored in a git repository on the Hugging Face Hub.
- Is it free?
- Static Spaces are free. Gradio and Docker Spaces need a paid plan to create, with a limited free option on ZeroGPU for personal accounts. Read the current documentation.
- Who can see my code?
- That depends on visibility. Public Spaces show source and app to everyone, protected hide the source, and private hide both.
- What hardware does it run on?
- By default 16GB RAM, 2 CPU cores and 50GB of non-persistent disk, per Hugging Face’s documentation.
Where this comes from
Written from the maker’s own pages, read on 2026-10-13. Plans, limits and features change, so the page you land on is the source.
Each tool links to its maker’s own page. They are listed so you know what exists and what to learn, not ranked, and they are not endorsements. We are not affiliated with these companies. A tool can change or be renamed; the page you land on is the source.