AI models
Genie 2 (bio)
Training compute
3.2×10²⁰ FLOP
Parameters
15.7M
Published
May 24, 2024
Genie 2 (bio) is an AI model developed by Columbia University and Rutgers University (United States), first published in May 2024. It works in the biology domain, on tasks such as protein generation.
Training it took an estimated 3.2×10²⁰ FLOP of compute (estimation method: hardware). The model has 15,700,000 parameters. It was trained on roughly 150.7M datapoints. Training ran on 8 NVIDIA A100 for about 120 hours.
Access: Open weights (unrestricted). Its weights are openly available. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Columbia University, Rutgers University
- Country of organization
- United States
- Domain
- Biology
- Task
- Protein generation
- Training compute
- 3.2×10²⁰ FLOP
- Compute estimation method
- Hardware
- Parameters
- 15,700,000
- Dataset size
- 150.7M
- Training hardware
- NVIDIA A100
- Chips used
- 8
- Training time
- 120 h
- Chip-hours
- 960
- Training power draw
- 6.3 kW
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- 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