AI models
CoAtNet
Training compute
4.3×10²² FLOP
Parameters
2.4B
Published
Jun 9, 2021
CoAtNet is an AI model developed by Google, Google Research and Google Brain (United States), first published in June 2021. It works in the vision domain, on tasks such as image classification.
Training it took an estimated 4.3×10²² FLOP of compute (estimation method: hardware). The model has 2,440,000,000 parameters. It was trained on roughly 88.8T datapoints. Training ran on Google TPU v3. The compute alone is estimated at $2K in 2023 dollars.
Access: Unreleased. Its weights are not openly released. The reference paper has 1,589 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Google, Google Research, Google Brain
- Country of organization
- United States
- Domain
- Vision
- Task
- Image classification
- Training compute
- 4.3×10²² FLOP
- Compute estimation method
- Hardware
- Parameters
- 2,440,000,000
- Dataset size
- 88.8T
- Training hardware
- Google TPU v3
- Chip-hours
- 10.1K
- Training cost (2023 USD)
- $2K
- Model accessibility
- Unreleased
- Open weights
- No
- Citations
- 1,589
- Epoch confidence
- Confident
More from Google,Google Research,Google Brain
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