AI models
ProteinGAN
Training compute
4.3×10¹⁸ FLOP
Parameters
60M
Published
Mar 4, 2021
ProteinGAN is an AI model developed by Vilnius University and Chalmers University of Technology (Lithuania and Sweden), first published in March 2021. It works in the biology domain, on tasks such as proteins and protein generation.
Training it took an estimated 4.3×10¹⁸ FLOP of compute (estimation method: hardware). The model has 60,000,000 parameters. Training ran on 1 NVIDIA P100 for about 210 hours.
Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Vilnius University, Chalmers University of Technology
- Country of organization
- Lithuania, Sweden
- Domain
- Biology
- Task
- Proteins, Protein generation
- Training compute
- 4.3×10¹⁸ FLOP
- Compute estimation method
- Hardware
- Parameters
- 60,000,000
- Training hardware
- NVIDIA P100
- Chips used
- 1
- Training time
- 210 h
- Chip-hours
- 210
- Training power draw
- 279 W
- 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