MACE-MP-0
Cambridge (Csányi Lab)
Universal foundation model for atomistic simulations covering 89 elements. Pre-trained on the Materials Project dataset, generalizes across organic molecules, inorganic crystals, and interfaces without fine-tuning.
Best For
Zero-shot atomistic simulation across diverse chemistries; rapid prototyping before fine-tuning
License
Open Source (MIT)
Strengths
- +89 elements covered
- +Zero-shot generalization
- +MIT license
- +Integrates with ASE/OpenMM
Limitations
- −Not specialized for drug-like molecules (see MACE-OFF24)
- −Accuracy varies by chemistry
- −Slower than classical force fields
R&D Pipeline Coverage
Related Tools
MACE-OFF24
Cambridge (Csányi Lab)
Equivariant ML force field for organic molecules covering H, C, N, O, F, P, S, Cl, Br, I (~90% of drug-like space). Near-DFT accuracy for torsion profiles.
OpenMM 8.5
Stanford / OpenMM Community
Python-first MD framework with native ML potential API (openmm-ml). Wraps MACE, NequIP, AceFF, and other ML force fields directly.
GROMACS 2026
GROMACS Consortium (KTH, Max Planck, et al.)
High-performance all-atom and coarse-grained MD engine. GROMACS 2026 added native NNP/MM support for hybrid ML-classical simulations.
More in MD & Simulation
GROMACS 2026
GROMACS Consortium (KTH, Max Planck, et al.)
High-performance all-atom and coarse-grained MD engine. GROMACS 2026 added native NNP/MM support for hybrid ML-classical simulations.
OpenMM 8.5
Stanford / OpenMM Community
Python-first MD framework with native ML potential API (openmm-ml). Wraps MACE, NequIP, AceFF, and other ML force fields directly.
AMBER 24
AMBER Consortium (UCSF et al.)
MD suite with best-in-class GPU acceleration (pmemd.cuda) and strong force field ecosystem. Now includes NNP integration via DeePMD-GNN.
Stay updated on MACE-MP-0
Weekly newsletter covering AI tool releases, benchmarks, and what practitioners actually use.