AI models
IgGM
Training compute
8.6×10²⁰ FLOP
Published
Sep 22, 2024
IgGM is an AI model developed by Chinese Academy of Sciences, University of Chinese Academy of Sciences and Tencent (China), first published in September 2024. It works in the biology domain, on tasks such as protein design.
Training it took an estimated 8.6×10²⁰ FLOP of compute (estimation method: hardware). It was trained on roughly 15.5M datapoints. Training ran on 8 NVIDIA A100 for about 240 hours.
Access: Open weights (non-commercial). Its weights are openly available. Epoch AI rates the confidence of this record as likely.
Full record
- Organization
- Chinese Academy of Sciences, University of Chinese Academy of Sciences, Tencent
- Country of organization
- China
- Domain
- Biology
- Task
- Protein design
- Training compute
- 8.6×10²⁰ FLOP
- Compute estimation method
- Hardware
- Dataset size
- 15.5M
- Training hardware
- NVIDIA A100
- Chips used
- 8
- Training time
- 240 h
- Training power draw
- 6.3 kW
- Model accessibility
- Open weights (non-commercial)
- Open weights
- Yes
- Epoch confidence
- Likely
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