Apple Silicon · MLX · Metal

Atomistic simulation,
native to your Mac.

An MD and DFT runtime built directly on MLX and Metal — it runs the GPU on your machine, not a wrapper around someone else's cluster.

Get started View on GitHub

Capabilities

One runtime, two scales.

Apple Silicon native

MLX arrays and Metal kernels drive the GPU on your machine. No CUDA, no server, no cloud.

Plane-wave DFT

Kohn–Sham SCF, LDA + PBE via autodiff, Γ-point and k-mesh, Davidson diagonalization.

Molecular mechanics

Lennard-Jones, Coulomb, harmonic bonds and angles, periodic + RB torsions, bounded PME, Langevin NVT.

Pseudopotentials

GTH and UPF readers, local + nonlocal projectors, analytic and finite-difference forces.

Python 3.13 · uv

Reproducible environments, fast sync, Jupyter-first exploration.

Reference-validated

OpenMM and LAMMPS reference surfaces keep the MLX runtime honest, run after run.

LDA · PBE

XC functionals

NVE · NVT

Integrators

PME

Long-range electrostatics

Jupyter

First-class visualization

Quick start

Up and running in three lines.

zsh — mlx-atomistic

$ uv venv --python 3.13
$ uv sync --extra notebook --group dev
$ uv run jupyter lab

# run a DFT SCF benchmark
$ uv run python -m mlx_atomistic.benchmarks.dft_scf \
    --sizes 8,16,24,32 --iterations 5 --mixer both --json

Atomistic simulation, native to your Mac.