Software Download

We recommend all users upgrade to the latest version for the best performance and features.

Stable Release

Latest Stable Release GPUMD-v5.4

GPUMD-v5.4 Highlights

Bug Fixes and New Features

Download v5.4 Now

Updates for the nep executable:

  • Make non-full-batch training faster. #1511
  • Removed the q_1122 5-body descriptor introduced in GPUMD-v5.3. #1519
  • Added more 4-body descriptors (q_123, q_233, q_134). #1517 #1527

Quick Start

Deploy GPUMD in your environment in just three steps.

Step 01

Prepare Env

Load the CUDA compilation environment.

module load cuda
Step 02

Unzip Source

Unzip the downloaded ZIP package.

unzip GPUMD.zip
Step 03

Compile

Enter src directory and run make.

cd GPUMD/src && make

Official Manual

Includes complete input/output formats and simulation examples.

Read Online PDF Download

Version Archive

Need an older version? Check the version history here.

View All Releases on GitHub
Archive v5.0

v5.0

Mar 2026

Introduced gpumd-mdi.

Download Source (ZIP)
Archive v4.9.1

v4.9.1

Feb 2026

Bug fixes and performance improvements.

Download Source (ZIP)
Archive v4.9

v4.9

Feb 2026

Accelerated GPUMD simulation speed.

Download Source (ZIP)
Archive v4.8

v4.8

Jan 2026

Supported fine-tuning descriptors; introduced lambda_q and lambda_z loss weights; released gnep executable.

Download Source (ZIP)
Archive v4.7

v4.7

Dec 2025

Introduced a new typewise cutoff scheme, further enhancing force field definition flexibility.

Download Source (ZIP)
Archive v4.6

v4.6

Nov 2025

Officially introduced qNEP machine learning potential model, supporting high-precision simulation of charged systems.

Download Source (ZIP)
Archive v4.5

v4.5

Oct 2025

Added support for ADP (Angular Dependent Potential) force fields.

Download Source (ZIP)

Citation

If your research work or product uses GPUMD, please cite the following article:

GPUMD 4.0: A high-performance molecular dynamics package for versatile materials simulations with machine-learned potentials

Authors: Ke Xu, Hekai Bu, Shuning Pan, Eric Lindgren, Yongchao Wu, Yong Wang, Jiahui Liu, Keke Song, Bin Xu, Yifan Li, Tobias Hainer, Lucas Svensson, Julia Wiktor, Rui Zhao, Hongfu Huang, Cheng Qian, Shuo Zhang, Zezhu Zeng, Bohan Zhang, Benrui Tang, Yang Xiao, Zihan Yan, Jiuyang Shi, Zhixin Liang, Junjie Wang, Ting Liang, Shuo Cao, Yanzhou Wang, Penghua Ying, Nan Xu, Chengbing Chen, Yuwen Zhang, Zherui Chen, Xin Wu, Wenwu Jiang, Esme Berger, Yanlong Li, Shunda Chen, Alexander J. Gabourie, Haikuan Dong, Shiyun Xiong, Ning Wei, Yue Chen, Jianbin Xu, Feng Ding, Zhimei Sun, Tapio Ala-Nissila, Ari Harju, Jincheng Zheng, Pengfei Guan, Paul Erhart, Jian Sun, Wengen Ouyang, Yanjing Su, Zheyong Fan

Journal: Materials Genome Engineering Advances

Year: 2025

Volume: 3

Pages: e70028

DOI: 10.1002/mgea.70028
View Full Text