AI models
ESM-GearNet
Training compute
2.1×10¹⁹ FLOP
Parameters
650M
Published
May 11, 2023
ESM-GearNet is an AI model developed by Mila - Quebec AI (originally Montreal Institute for Learning Algorithms), University of Montreal / Université de Montréal, IBM Research, HEC Montreal and CIFAR AI Research (Canada and United States), first published in May 2023. It works in the biology domain, on tasks such as proteins and protein function prediction.
Training it took an estimated 2.1×10¹⁹ FLOP of compute. The model has 650,000,000 parameters. It was trained on roughly 109.5M datapoints. Training ran on 4 NVIDIA A100.
The reference paper has 53 citations. Epoch AI rates the confidence of this record as likely.
Full record
- Organization
- Mila - Quebec AI (originally Montreal Institute for Learning Algorithms), University of Montreal / Université de Montréal, IBM Research, HEC Montreal, CIFAR AI Research
- Country of organization
- Canada, United States
- Domain
- Biology
- Task
- Proteins, Protein function prediction
- Training compute
- 2.1×10¹⁹ FLOP
- Parameters
- 650,000,000
- Dataset size
- 109.5M
- Training hardware
- NVIDIA A100
- Chips used
- 4
- Training power draw
- 3.2 kW
- Citations
- 53
- Epoch confidence
- Likely
More from Mila - Quebec AI (originally Montreal Institute for Learning Algorithms),University of Montreal / Université de Montréal,IBM Research,HEC Montreal,CIFAR AI Research
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