UMA — Universal Models for Atoms
~10,000x faster than DFT — a universal model for atoms
Latest: UMA-1.2 (March 2026) — ~50% faster, ~40% more accurate on the OMol25 test set
A family of machine-learned interatomic potentials trained on about half a billion 3D atomic structures across molecules, materials and catalysts — FAIR Chemistry's 'one model for all of chemistry.' Using a Mixture of Linear Experts architecture, UMA matches DFT-level end results roughly 10,000x faster, and powers downstream tools like FastCSP for crystal-structure prediction (August 2025).
Why it matters
One interatomic potential for molecules, materials and catalysts, trained on about half a billion 3D structures with a mixture-of-linear-experts design that adds capacity without slowing inference. It delivers DFT-level results roughly 10,000x faster and powers downstream tools such as FastCSP for crystal-structure prediction.
Facts
- Trained on ~500 million unique 3D structures — likely the largest atomistic training corpus assembled; October 2025 added multi-node/multi-GPU and LAMMPS interfaces for large-scale molecular dynamics.
Try it yourself
Official UMA demo (Hugging Face Space) ↗ Checkpoints on Hugging Face ↗ Read the paper ↗
Lineage
Sources
arXiv ↗GitHub · fairchem ↗Meta AI research ↗