AI models
ST-MoE
Training compute
2.9×10²³ FLOP
Parameters
269B
Published
Feb 17, 2022
ST-MoE is an AI model developed by Google, Google Brain and Google Research (United States), first published in February 2022. It works in the language domain, on tasks such as language modeling/generation.
Training it took an estimated 2.9×10²³ FLOP of compute (estimation method: operation counting). The model has 269,000,000,000 parameters. It was trained on roughly 1.5T datapoints.
Access: Unreleased. Its weights are not openly released. The reference paper has 375 citations. Epoch AI rates the confidence of this record as likely.
Full record
- Organization
- Google, Google Brain, Google Research
- Country of organization
- United States
- Domain
- Language
- Task
- Language modeling/generation
- Training compute
- 2.9×10²³ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 269,000,000,000
- Dataset size
- 1.5T
- Numerical format
- BF16
- Model accessibility
- Unreleased
- Open weights
- No
- Citations
- 375
- Epoch confidence
- Likely
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