Left: Model forward pass speed (excluding featurization) compared to MACE on a single NVIDIA A100 GPU. At large system sizes, Orb is between 3 to 6 times faster than MACE. Right: End to end model inference speed for a 100 atom system on a single NVIDIA A100 when implemented as a Calculator object in the Atomic Simulation Environment Python library. The D3 dispersion correction adds a substantial cost which is amortized by Orb models, as the corrections are incorporated into training datasets. All measurements reported as the median of 50 runs.
How this file is connected to other assets
Discover other files like this one
Authors introduce Orb, a family of universal interatomic potentials for atomistic modeling of materials. Orb models are 3-6 times faster than existing universal potentials, stable under simulation for a range of out of distribution materials and, upon release, represented a 31% reduction in error over other methods on the Matbench Discovery benchmark. https://arxiv.org/abs/2410.22570
Table S1 from the MatterSim paper
Plot produced by taking the features generated by Orb (256 dim output) and visualizing different dimensionality reduction methods on them and coloring the point by Tc from the 3DSC database.