AI models
AlphaFold-Multimer
Training compute
4.3×10²¹ FLOP
Published
Oct 4, 2021
AlphaFold-Multimer is an AI model developed by Google DeepMind and DeepMind (United States and United Kingdom), first published in October 2021. It works in the biology domain, on tasks such as protein folding prediction and proteins.
Training it took an estimated 4.3×10²¹ FLOP of compute (estimation method: hardware). It was trained on roughly 56.6M datapoints. Training ran on 64 Google TPU v3 for about 384 hours. The compute alone is estimated at $8K in 2023 dollars.
Access: Open weights (unrestricted). Its weights are openly available. It is built on top of AlphaFold 2. The reference paper has 2,694 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Google DeepMind, DeepMind
- Country of organization
- United States, United Kingdom
- Domain
- Biology
- Task
- Protein folding prediction, Proteins
- Training compute
- 4.3×10²¹ FLOP
- Compute estimation method
- Hardware
- Dataset size
- 56.6M
- Training hardware
- Google TPU v3
- Chips used
- 64
- Training time
- 384 h
- Chip-hours
- 24.6K
- Training power draw
- 58.1 kW
- Training cost (2023 USD)
- $8K
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Base model
- AlphaFold 2
- Citations
- 2,694
- 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