NVIDIA open-sources Kumo Tabular foundation models for tabular data with permissive license
jure · x · 2026-09-29
NVIDIA has launched Kumo Tabular, a family of pretrained foundation models for tabular classification and regression, claiming a new Pareto frontier across the accuracy–inference-time tradeoff.
Key points:
- The models use labeled examples as context to predict outputs for new data, in-context learning style — no fine-tuning required
- Fully open: open weights, open-source software, and a permissive OpenMDW 1.1 license for commercial use
- Available on Hugging Face (nvidia/Kumo-Tabular); inference via the structured-data-models package with CUDA support
- Sample code shows building a TableTensor from a pandas DataFrame and running KumoTabular classification to get class probabilities
Related event: NVIDIA Open-Sources Kumo Tabular Foundation Models for Tabular Data(3 posts)→
More from Models
- Opus 5.5 Generates a Gorgeous Scrollable 3D Explainer on Chipmaking — threepointone · 2026-09-29
- Why steering vectors work on complex models: a new post offers three intuitions — gleech · 2026-09-29
- OpenAI Pushes Pre-Event Update, Wiping Users' Custom Sprite Sheets — whurley · 2026-09-29
- UsageBench launches to track AI subscription usage cuts, starting with Claude Max 20x and ChatGPT Pro — alejandroll10 · 2026-09-29
- Hidden CoT and failing distillation: open-weight models set to fall further behind frontier labs — toptickcrypto · 2026-09-29
- OpenAI Explains $200 Plan Quota Change Ahead of Dev Day — that_90s_guy · 2026-09-29