NVIDIA releases Kumo Tabular, an open model for tabular data
NVIDIA has released Kumo Tabular, an open foundation model for tabular data that predicts labels for new rows from a table containing labeled examples. It handles classification and regression in a single forward pass, without training, hyperparameter tuning or feature engineering during use, and is available on Hugging Face through an open-source library.
Pretrained only on artificial data, Kumo Tabular comes in three sizes, from 28 million to 215 million parameters, and is released under the OpenMDW-1.1 license, which allows commercial use. NVIDIA says the model ranked first on the TabArena, BeyondArena, TALENT and ScoringBench benchmarks.
Why it matters · editorial interpretation
Its release under a license allowing commercial use may make it easier for teams to evaluate open tabular models for classification and regression without an additional training cycle during use. The benchmark rankings cited by NVIDIA provide initial reference points for that evaluation, but do not replace testing on real-world data.