AI models
DeiT-B
Training compute
7.9×10¹⁹ FLOP
Parameters
86M
Published
Jan 15, 2021
DeiT-B is an AI model developed by Meta AI and Sorbonne University (United States and France), first published in January 2021. It works in the vision domain, on tasks such as image classification.
Training it took an estimated 7.9×10¹⁹ FLOP of compute (estimation method: hardware). The model has 86,000,000 parameters. It was trained on roughly 3.8M datapoints. Training ran on NVIDIA V100 for about 53 hours.
Access: Open weights (unrestricted). Its weights are openly available. The reference paper has 9,077 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Meta AI, Sorbonne University
- Country of organization
- United States, France
- Domain
- Vision
- Task
- Image classification
- Training compute
- 7.9×10¹⁹ FLOP
- Compute estimation method
- Hardware
- Parameters
- 86,000,000
- Dataset size
- 3.8M
- Training hardware
- NVIDIA V100
- Training time
- 53 h
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Citations
- 9,077
- 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