AI4SDB
Home/Tools/Chemistry & Materials Science/MACE

Chemistry & Materials Science

MACE

An open-source PyTorch framework for training and deploying machine-learning interatomic potentials with higher-order equivariant message passing.

Last verified

RESEARCH USE

Where MACE fits

MACE is most relevant for training, fine-tuning, and deploying interatomic potentials for materials and molecules. It should be treated as one component of a research workflow rather than as a substitute for reading source material, checking methods, or validating scientific conclusions.

What to evaluate before use

  • Check whether its Python, Linux, GPU, HPC workflow fits your existing research environment and export requirements.
  • The recorded access model is open source; limits, institutional terms, and commercial-use conditions may change.
  • Open-source code is available, but code, model weights, hosted services, and data may have different licenses. Review the relevant terms separately.

Verification note

This entry summarizes the tool's role without assessing scientific accuracy or endorsing its outputs. Features and terms can change; consult the official source before adopting it for consequential work.

machine-learning potentialsatomistic simulation

Last verified: 2026-09-01
Source: official documentation ↗