AI models
DecompDiff
Training compute
1.9×10¹⁹ FLOP
Published
Feb 26, 2024
DecompDiff is an AI model developed by University of Illinois Urbana-Champaign (UIUC), ByteDance, University of Chinese Academy of Sciences, Chinese Academy of Sciences and Tsinghua University (United States and China), first published in February 2024. It works in the biology domain, on tasks such as drug discovery.
Training it took an estimated 1.9×10¹⁹ FLOP of compute (estimation method: hardware). It was trained on roughly 12.5M datapoints. Training ran on 1 NVIDIA A100 for about 41.7 hours.
The reference paper has 119 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- University of Illinois Urbana-Champaign (UIUC), ByteDance, University of Chinese Academy of Sciences, Chinese Academy of Sciences, Tsinghua University
- Country of organization
- United States, China
- Domain
- Biology
- Task
- Drug discovery
- Training compute
- 1.9×10¹⁹ FLOP
- Compute estimation method
- Hardware
- Dataset size
- 12.5M
- Training hardware
- NVIDIA A100
- Chips used
- 1
- Training time
- 42 h
- Training power draw
- 435 W
- Citations
- 119
- 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