What it does
TabPFN is a foundation model for tabular data, meaning data arranged in rows and columns, like a spreadsheet. It can sort rows into groups (classification) or predict numbers (regression).
Unlike many methods, you do not have to train a model from scratch. You give it your table and it makes predictions straight away, downloading its model file the first time.
A graphics card is recommended. On a normal processor it handles only moderate amounts of data, and its makers offer a free hosted option for people without one.
Who it's for
Data scientists, analysts and researchers who work with tables of data.
Can I use it without coding?
Developers only. It is a Python library; there is an online notebook tutorial to try it. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Mac, Linux, Windows
- Computer
- Works best on a powerful computer or one with a graphics card (GPU)
- Privacy
- Your choice: run it on your device or use an online service
- API key
- Not needed
Try it
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (Apache-2.0): Permissive: free to use, change and share, including for business.
- More on staying safe
Where people are talking about it
- TabPFN-3.5 model reportResearch paper · Sept 2026
- TabPFN-3 technical reportResearch paper · May 2026
- Show HN: TabPFN MCP, gives LLMs tools for predictions on tabular data (beta)Hacker News · Feb 2026
- Show HN: TabPFN-2.5 – SOTA foundation model for tabular dataHacker News · Nov 2025
- TabPFN-2.5 model reportResearch paper · Nov 2025