AI models
ViT + DINO
Training compute
2.1×10²⁰ FLOP
Parameters
85M
Published
Apr 29, 2021
ViT + DINO is an AI model developed by INRIA and Facebook AI Research (France and United States), first published in April 2021. It works in the vision domain, on tasks such as image classification.
Training it took an estimated 2.1×10²⁰ FLOP of compute (estimation method: hardware). The model has 85,000,000 parameters. It was trained on roughly 1.3M datapoints. Training ran on NVIDIA V100. The compute alone is estimated at $380 in 2023 dollars.
Access: Open weights (unrestricted). Its weights are openly available. The reference paper has 9,037 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- INRIA, Facebook AI Research
- Country of organization
- France, United States
- Domain
- Vision
- Task
- Image classification
- Training compute
- 2.1×10²⁰ FLOP
- Compute estimation method
- Hardware
- Parameters
- 85,000,000
- Dataset size
- 1.3M
- Training hardware
- NVIDIA V100
- Training cost (2023 USD)
- $380
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Citations
- 9,037
- 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