OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Tabpfn

Tabpfn is the public PriorLabs Python implementation of TabPFN, a foundation model for tabular-data machine learning. It provides local PyTorch-based inference for classification and regression, with a separate cloud client and ecosystem extensions.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Tabpfn — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Tabpfn when a Python workflow needs a foundation-model approach to structured tabular classification or regression and the available hardware and model-weight terms fit the intended use.

Who it is for

  • Python data scientists working with structured datasets
  • Developers building classification or regression pipelines
  • Business users and prototypers using the documented no-code TabPFN UX

Documented uses

  • Fit a tabular classification model
  • Fit a tabular regression model
  • Generate predictions for unseen structured data
  • Use local GPU-accelerated inference or a separate cloud-inference client
  • Extend workflows with interpretability, embeddings, unsupervised tools or many-class support
Before you choose

Requirements & limits

The repository is public and licensed under Apache-2.0. Python 3.10 or newer is supported. Model weights are licensed separately, and several listed versions have non-commercial terms.

  • Choose local inference when the workflow can provide the required Python and PyTorch environment.
  • Use the documented cloud client when local hardware is not suitable.
  • GPU use is recommended; CPU-only operation is limited to moderate datasets, with sample limits varying by model version.
  • Check the separate license for the model weights selected for the workflow.
  • The core package supports classification and regression, while extensions cover additional workflows such as interpretability and embeddings.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install TabPFN and prepare a local Python workflow

Set up the TabPFN package for local tabular classification or regression.

Before you start

  • Python 3.10 or newer
  • A Python environment with PyTorch installed as required by the hardware setup
  • A GPU is recommended; CPU-only use is supported for moderate datasets

Steps

  1. Install the package with the command below.

    Documented command
    pip install tabpfn

  2. For Nvidia, AMD or CPU-only systems, install the corresponding PyTorch build before installing TabPFN where the repository instructions require it.

  3. Import TabPFNClassifier or TabPFNRegressor from tabpfn.

  4. Create the model, call fit(X_train, y_train), and use predict(X_test) for the selected task.

Expected outcome

A local Python workflow is configured for fitting a TabPFN classifier or regressor and producing predictions.

Guide limitations

  • A model checkpoint downloads on first use.
  • GPU memory and CPU sample limits affect feasible dataset sizes.
  • Model weights have licensing terms separate from the Apache-2.0 code license.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
2 October 2026
Original website title
PriorLabs/TabPFN · Official homepage title · retained in its source language
How we review sourcesSuggest a correction