AI models
ESM3-open-small
Training compute
2.7×10²¹ FLOP
Parameters
1.4B
Published
Jun 25, 2024
ESM3-open-small is an AI model developed by EvolutionaryScale and University of California (UC) Berkeley (United States), first published in June 2024. It works in the biology domain, on tasks such as protein generation.
Training it took an estimated 2.7×10²¹ FLOP of compute (estimation method: reported). The model has 1,400,000,000 parameters. It was trained on roughly 48B datapoints.
Access: Open weights (non-commercial). Its weights are openly available. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- EvolutionaryScale, University of California (UC) Berkeley
- Country of organization
- United States
- Domain
- Biology
- Task
- Protein generation
- Training compute
- 2.7×10²¹ FLOP
- Compute estimation method
- Reported
- Parameters
- 1,400,000,000
- Dataset size
- 48B
- Model accessibility
- Open weights (non-commercial)
- Open weights
- Yes
- Epoch confidence
- Confident
More from EvolutionaryScale,University of California (UC) Berkeley
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