metaai·lightalo unofficial · independent
Universe / AI for Science / UMA — Universal Models for Atoms
AI for Science · 2025

UMA — Universal Models for Atoms

~10,000x faster than DFT — a universal model for atoms

open source UMA-M: 1.4B total, ~50M active per structure params

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

Try it yourself

Lineage

Descends fromOpen Catalyst ProjectOpen Molecules 2025Open Materials 2024OpenDAC / ODAC25
Led tofairchem

See the whole family tree →

Sources

More in AI for Science

Brain2QwertyBrain & AI: Decoding Perception from MEG/EEGESM / ESMFold

Read the AI for Science story on the sky →

✦ Open on the map Explore AI for Science Quiz me