Ångstrom AI (YC S24), with the University of Cambridge (the Csanyi group) and AstraZeneca, released DFT Accuracy on Crystal Structure Prediction with Machine Learning Interatomic Potentials. The paper presented CSP-MACE-Å, a machine learning model designed to match DFT accuracy in crystal structure prediction while running 10,000 times faster.

CSP-MACE-Å also significantly outperformed UMA-OMC on crystal-structure prediction benchmarks. UMA is Meta's general-purpose model for atoms and molecules; UMA-OMC is the version adapted for organic molecular crystals.

Ångstrom built CSP-MACE-Å on anycloud, a CLI that runs GPU workloads across your own cloud accounts. The team ran more than 100,000 GPU hours, almost entirely on spot capacity across multiple clouds. Researchers also used agents through the same anycloud CLI to launch and monitor batches, retrieve results, and help drive the experiment loop.

Machine learning interatomic potentials (MLIPs) are replacing classical force fields in many computational chemistry applications, reducing simulation times from weeks of DFT compute to minutes on a single GPU. This post is a practical guide to training your own MLIP on cloud GPU spot instances: which architecture to pick, what it actually costs, and how to keep training going through preemption.