AI models
ESM1v
Training compute
1.4×10²⁰ FLOP
Parameters
650M
Published
Nov 17, 2021
ESM1v is an AI model developed by Facebook AI Research, New York University (NYU) and University of California (UC) Berkeley (United States and France), first published in November 2021. It works in the biology domain, on tasks such as proteins, protein or nucleotide language model (plm/nlm) and protein pathogenicity prediction.
Training it took an estimated 1.4×10²⁰ FLOP of compute (estimation method: hardware). The model has 650,000,000 parameters. It was trained on roughly 22.1B datapoints. Training ran on 64 NVIDIA V100.
Access: Open weights (unrestricted). Its weights are openly available. The reference paper has 713 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Facebook AI Research, New York University (NYU), University of California (UC) Berkeley
- Country of organization
- United States, France
- Domain
- Biology
- Task
- Proteins, Protein or nucleotide language model (pLM/nLM), Protein pathogenicity prediction
- Training compute
- 1.4×10²⁰ FLOP
- Compute estimation method
- Hardware
- Parameters
- 650,000,000
- Dataset size
- 22.1B
- Training hardware
- NVIDIA V100
- Chips used
- 64
- Training power draw
- 38.7 kW
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Citations
- 713
- Epoch confidence
- Confident
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