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. MatterSim
Developer Tools
MatterSim icon

MatterSim

by Microsoft Research

MatterSim is a deep learning atomistic model that works across elements, temperatures and pressures. It is distributed as a Python package with pre-trained models.

Web app·Free

View on GitHub(opens in a new tab)

About MatterSim

Key features of MatterSim

  • Atomistic model across elements, temperatures and pressures
  • Two pre-trained checkpoints, small and larger
  • ASE calculator for energy, forces and stress
  • Fine-tuning script for custom datasets
  • Install from PyPI or from source
  • Runs on CUDA GPUs or CPU
  • Documentation site for deeper guidance

Who MatterSim is for

  • Materials scientists
  • Computational chemists running atomistic simulations
  • Researchers fine-tuning models on their own data

How to use MatterSim

  1. 1

    Step 1: Create a clean conda environment with a supported Python version.

  2. 2

    Step 2: Install the package with pip install mattersim.

  3. 3

    Step 3: Build an atomic structure with ASE and attach the MatterSim calculator.

  4. 4

    Step 4: Read the potential energy, forces and stress from the structure.

  5. 5

    Step 5: Optionally switch to the larger checkpoint or run the fine-tuning script on your own data.

MatterSim FAQ

Which checkpoint is loaded by default?

The smaller, faster one. You can load the larger, more accurate one by setting the load path on the calculator.

Can I fine-tune it?

Yes. The package includes a fine-tuning script that trains a pre-trained model on a custom dataset using torchrun.

Does it run on a Mac?

Yes, but on Apple Silicon the README recommends the CPU device because the MPS backend can show numerical instability.

How should I cite it in a paper?

Cite the MatterSim preprint and state the exact model version and checkpoint you used, not just the name MatterSim.

Details

Pricing
Free
Type
Web app
Categories
Developer ToolsResearch
Added
Sep 16, 2026
Microsoft Research iconPublisherMicrosoft Research

Built from public sources

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

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

Something wrong here?

More from Microsoft Research

View publisher
MatterGen iconMatterGenMicrosoft Research · FreeMatterGen is a generative model from Microsoft for designing inorganic materials across the periodic table. It can be fine-tuned to steer generation toward property constraints.Developer Tools · FreeBiomedCLIP iconBiomedCLIPMicrosoft Research · FreeBiomedCLIP is a biomedical vision-language model from Microsoft, pretrained on 15 million figure-caption pairs from PubMed Central. It supports retrieval, image classification and visual question answering research.Developer Tools · FreeAurora iconAuroraMicrosoft Research · FreeAurora uses AI for AI foundation model for Earth-system prediction across weather, air quality, ocean, and environmental forecasting tasks.Data · Free

Related tools

See more
CHGNet iconCHGNetUniversity of California San Diego · FreeCHGNet 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.Developer Tools · FreeOmegaFold iconOmegaFoldHelixon · FreeProtein structure prediction model using a protein language model without requiring multiple sequence alignmentsDeveloper Tools · FreeHumanloop Evals iconHumanloop EvalsHumanloop · Contact for pricingHumanloop Evals is an AI-native product for evaluation and prompt-management platform for testing and improving LLM applications with datasets, evaluators, an.Developer Tools · Contact for pricing