AI models
Fugaku-LLM
Training compute
3×10²² FLOP
Parameters
13B
Published
May 10, 2024
Fugaku-LLM is an AI model developed by Tohoku University, CyberAgent, Tokyo Institute of Technology, Fujitsu, RIKEN, Nagoya University and Kotoba Technologies (Japan), first published in May 2024. It works in the language domain, on tasks such as language modeling, translation, japanese language modeling and 2 more.
Training it took an estimated 3×10²² FLOP of compute (estimation method: operation counting). The model has 13,000,000,000 parameters. It was trained on roughly 380B datapoints.
Access: Open weights (unrestricted). Its weights are openly available. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Tohoku University, CyberAgent, Tokyo Institute of Technology, Fujitsu, RIKEN, Nagoya University, Kotoba Technologies
- Country of organization
- Japan
- Domain
- Language
- Task
- Language modeling, Translation, Japanese language modeling, Language modeling/generation, Question answering
- Training compute
- 3×10²² FLOP
- Compute estimation method
- Operation counting
- Parameters
- 13,000,000,000
- Dataset size
- 380B
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- 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