Ploba logo

Find the right AI tool for the job: apps, agents, APIs, MCP servers and datasets, explained plainly.

Get the AI Digest

Discover

  • Explore
  • Top Charts
  • Categories
  • Agents
  • MCP servers
  • Developer tools

Learn & community

  • Learn AI
  • AI Glossary
  • Blog
  • Hackathons
  • People
  • AI Digest

For makers

  • List your tool
  • Docs
  • Claim a listing
  • Advertise
  • Write for us

Company

  • About
  • Careers
  • Changelog
  • Trust
  • Security
  • Contact

© 2026 Ploba. All rights reserved.

  • Privacy
  • Terms
  • Cookies
  • Advertising
  • All policies
llms.txt
Ploba logo
DiscoverHackathonsPeopleLearnAI Digest
Sign inGet started
HomeTop ChartsExploreCategories
TypesWeb apps1,894Agents585Plugins416APIs376Mobile apps152Datasets85
AdvertisingYour product hereReach people browsing AI tools on Ploba.Advertise hereAdvertisingYour product hereReach people browsing AI tools on Ploba.Advertise here
  1. Explore
  2. /
  3. Developer Tools
  4. /
  5. CHGNet
Developer Tools
CHGNet icon

CHGNet

by University of California San Diego

CHGNet is a pretrained universal neural network potential for charge-informed atomistic modeling. It predicts energy, force, stress and magnetic moments of crystal structures at near DFT accuracy.

Web app·Free

View on GitHub(opens in a new tab)

About CHGNet

Key features of CHGNet

  • Pretrained on more than 1.5 million Materials Project structures
  • Predicts energy, forces, stress and magnetic moments
  • Structure relaxation
  • Molecular dynamics via ASE or LAMMPS
  • Fine tuning to your own system
  • Runs on CPU, CUDA, XPU and MPS
  • Colab example notebooks

Who CHGNet is for

  • Computational materials scientists
  • Researchers studying charge distribution and electron interactions in crystals
  • Teams running phonon or elastic property workflows

How to use CHGNet

  1. 1

    Step 1: Install the package with pip install chgnet.

  2. 2

    Step 2: Load the pretrained model with CHGNet.load().

  3. 3

    Step 3: Read a structure with pymatgen and call predict_structure.

  4. 4

    Step 4: Run relaxation or molecular dynamics with the included classes.

  5. 5

    Step 5: Fine tune the model on your system using the tuning notebook.

CHGNet FAQ

What does CHGNet predict?

Energy in eV per atom, forces, stress in GPa and magnetic moments for a given structure.

Which pretrained models are offered?

A default model trained on Materials Project trajectories, a deprecated earlier version, and an r2scan-level model. Newer MatPES-based checkpoints live in the MatGL repo.

What hardware does it run on?

CPU, NVIDIA GPUs, Intel GPUs and Apple silicon. The device is picked automatically and can be overridden per call or with an environment variable.

Can I fine tune it?

Yes. The Tuning CHGNet notebook shows how to fine tune the pretrained model to your system.

Details

Pricing
Free
Type
Web app
Categories
Developer ToolsResearch
Added
Sep 16, 2026
University of California San Diego iconPublisherUniversity of California San Diego

Built from public sources

We put this page together from CHGNet’s own website and docs so you can compare it with other tools. Ploba isn’t affiliated with CHGNet.

Work at CHGNet? Claim the listing to manage it yourself.

Something wrong here?

Related tools

See more
Boltz-2 iconBoltz-2Boltz · FreeBiomolecular AI model extending structure prediction toward molecular interaction and binding-affinity modelingDeveloper Tools · FreeDeepCell iconDeepCellVan Valen Lab · FreeDeep-learning platform and models for cell segmentation, tracking, and quantitative analysis of microscopy imagesDeveloper Tools · FreeDeepImageJ iconDeepImageJDeepImageJ · FreeDeepImageJ is a plugin that lets you run pre-trained deep learning models inside ImageJ and Fiji. It needs no deep learning expertise or programming skills.Developer Tools · Free