AI models
ESM-AA
Training compute
7.3×10²⁰ FLOP
Parameters
35M
Published
Apr 5, 2024
ESM-AA is an AI model developed by Peking University, Nanjing University, Tsinghua University and PharMolix (China), first published in April 2024. It works in the biology domain, on tasks such as protein folding prediction, protein or nucleotide language model (plm/nlm) and proteins.
Training it took an estimated 7.3×10²⁰ FLOP of compute (estimation method: hardware). The model has 35,000,000 parameters. It was trained on roughly 1.1B datapoints. Training ran on 16 NVIDIA A100 for about 72 hours.
It is built on top of ESM2-35M. The reference paper has 19 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Peking University, Nanjing University, Tsinghua University, PharMolix
- Country of organization
- China
- Domain
- Biology
- Task
- Protein folding prediction, Protein or nucleotide language model (pLM/nLM), Proteins
- Training compute
- 7.3×10²⁰ FLOP
- Compute estimation method
- Hardware
- Parameters
- 35,000,000
- Dataset size
- 1.1B
- Training hardware
- NVIDIA A100
- Chips used
- 16
- Training time
- 72 h
- Training power draw
- 12.7 kW
- Base model
- ESM2-35M
- Citations
- 19
- 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