AI models
MatterSim (M3GNet - MatterSim-v1.0.0-5M)
Training compute
1.6×10¹⁶ FLOP
Parameters
4.5M
Published
May 10, 2024
MatterSim (M3GNet - MatterSim-v1.0.0-5M) is an AI model developed by Microsoft Research AI for Science (United States), first published in May 2024. It works in the materials science domain, on tasks such as atomistic simulations and molecular simulation.
Training it took an estimated 1.6×10¹⁶ FLOP of compute (estimation method: operation counting). The model has 4,500,000 parameters. Training ran on 8 NVIDIA A100.
Access: Open weights (unrestricted). Its weights are openly available. Epoch AI rates the confidence of this record as speculative.
Full record
- Organization
- Microsoft Research AI for Science
- Country of organization
- United States
- Domain
- Materials science
- Task
- Atomistic simulations, Molecular simulation
- Training compute
- 1.6×10¹⁶ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 4,500,000
- Training hardware
- NVIDIA A100
- Chips used
- 8
- Training power draw
- 6.3 kW
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Epoch confidence
- Speculative
More from Microsoft Research AI for Science
SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.
← All ai models