Loading...
Not exactly the most rigorous test, but this side-by-side comparison shows the difference between running MD locally (M2 Macbook Air) and on a proper server (g4dn.2xl with T4 GPU). Each log is actually 100 simulation steps too.
Discover other files like this one
Table S5 from the MatterSim paper: Comparison of property prediction performance for M3GNet and Graphormer models.
Table S1 from the MatterSim paper