AI models
CLUE
Training compute
3.5×10¹⁸ FLOP
Parameters
160M
Published
Nov 22, 2022
CLUE is an AI model developed by Naver Clova and Naver AI Lab (South Korea), first published in November 2022. It works in the recommendation domain, on tasks such as recommender system.
Training it took an estimated 3.5×10¹⁸ FLOP of compute (estimation method: reported,operation counting). The model has 160,000,000 parameters. Training ran on 64 NVIDIA V100 for about 168 hours.
Epoch AI rates the confidence of this record as likely.
Full record
- Organization
- Naver Clova, Naver AI Lab
- Country of organization
- South Korea
- Domain
- Recommendation
- Task
- Recommender system
- Training compute
- 3.5×10¹⁸ FLOP
- Compute estimation method
- Reported, Operation counting
- Parameters
- 160,000,000
- Training hardware
- NVIDIA V100
- Chips used
- 64
- Training time
- 168 h
- Training power draw
- 38.4 kW
- 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