QET-PES-MatPES-PBE-2025.2

Introduction

Pre-trained QET foundation potential, i.e., universal machine learning interatomic potential trained on the MatPES-PBE-2025.2 dataset.

Potential

matgl Potential model (version 3).

Usage

import matgl

model = matgl.load_model("materialyze/QET-PES-MatPES-PBE-2025.2")

Model Details

• Number of parameters: 905,492

Metrics

Split	Energy MAE (eV/atom)	Force MAE (eV/A)	Stress MAE (GPa)	Charge MAE (e)
Train	0.040025	0.121260	0.520767	0.031361
Validation	0.040638	0.138194	0.616641	0.031837
Test	0.041846	0.132441	0.628318	0.031398

Metadata

{
  "dataset": "MatPES-PBE-2025.2",
}