ChengRang

NVIDIA Kumo Tabular

AI Search & Research Open Source

An open-source tabular foundation model released by NVIDIA on September 29, 2026. It can perform classification and regression predictions in a single forward inference pass, without the need for training, hyperparameter tuning, or feature engineering.

NVIDIAopen-source modeltabular datamachine learningstructured data
Visit NVIDIA Kumo Tabular

Disclaimer: Review content represents our editorial team's views and experience, not commercial recommendation or investment advice. Product info and pricing may change; refer to official sources.

Overview

NVIDIA Kumo Tabular is an open-source tabular foundation model released by NVIDIA on September 29, 2026. It belongs to the NVIDIA Kumo Structured model series, and its weights are available on Hugging Face. It is designed for classification and regression tasks on tabular data. Its core feature is that it requires no task-specific training, hyperparameter tuning, feature engineering, or missing value imputation. You only need to provide a labeled table and the rows to be predicted, and the model returns classification probabilities or numerical predictions in a single forward pass. The model uses a Transformer designed around tabular structure, combining column attention, row attention, and context attention, and offers three sizes from 28M to 215M parameters. Pretraining uses entirely synthetic tables generated by a structural causal model sampler.

Key Features

Use Cases

Pros

Pricing

This model is open source, uses the OpenMDW-1.1 license, allows commercial use, and its weights are available on Hugging Face. Specific pricing information is not provided; please refer to the official website.

Summary

NVIDIA Kumo Tabular is an open-source tabular foundation model released on September 29, 2026. It supports classification and regression in a single forward pass, with no training, hyperparameter tuning, feature engineering, or missing value imputation required. The model offers three sizes from 28M to 215M parameters, ranks first on TabArena, BeyondArena, TALENT, and ScoringBench, is 17x faster than LimiX-2 on a single RTX 6000 Pro, and uses the OpenMDW-1.1 license to allow commercial use.

Version History

Category
AI Search & Research
Pricing
Open Source
Tags
NVIDIA · open-source model · tabular data
Website

Related Tools