AI models
FoldFlow
Training compute
1.1×10²⁰ FLOP
Published
Oct 3, 2023
FoldFlow is an AI model developed by McGill University, Mila - Quebec AI (originally Montreal Institute for Learning Algorithms), Dreamfold, University of Montreal / Université de Montréal and University of Oxford (Canada and United Kingdom), first published in October 2023. It works in the biology domain, on tasks such as protein generation.
Training it took an estimated 1.1×10²⁰ FLOP of compute (estimation method: hardware). It was trained on roughly 40M datapoints. Training ran on 4 NVIDIA A100 for about 60 hours.
The reference paper has 165 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- McGill University, Mila - Quebec AI (originally Montreal Institute for Learning Algorithms), Dreamfold, University of Montreal / Université de Montréal, University of Oxford
- Country of organization
- Canada, United Kingdom
- Domain
- Biology
- Task
- Protein generation
- Training compute
- 1.1×10²⁰ FLOP
- Compute estimation method
- Hardware
- Dataset size
- 40M
- Training hardware
- NVIDIA A100
- Chips used
- 4
- Training time
- 60 h
- Training power draw
- 3.2 kW
- Citations
- 165
- 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