AI models
Refact-1.6B
Training compute
1.2×10²² FLOP
Parameters
1.6B
Published
Aug 29, 2023
Refact-1.6B is an AI model developed by Refact AI (United Kingdom), first published in August 2023. It works in the language domain, on tasks such as language modeling/generation.
Training it took an estimated 1.2×10²² FLOP of compute (estimation method: operation counting,hardware). The model has 1,600,000,000 parameters. It was trained on roughly 1.2T datapoints. Training ran on 6 NVIDIA RTX A5000 for about 672 hours.
Access: Open weights (restricted use). Its weights are openly available. Epoch AI rates the confidence of this record as likely.
Full record
- Organization
- Refact AI
- Country of organization
- United Kingdom
- Domain
- Language
- Task
- Language modeling/generation
- Training compute
- 1.2×10²² FLOP
- Compute estimation method
- Operation counting, Hardware
- Parameters
- 1,600,000,000
- Dataset size
- 1.2T
- Training hardware
- NVIDIA RTX A5000
- Chips used
- 6
- Training time
- 672 h
- Chip-hours
- 4K
- Training power draw
- 2.7 kW
- Model accessibility
- Open weights (restricted use)
- Open weights
- Yes
- 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