AI models
XGLM-7.5B
Training compute
2.3×10²² FLOP
Parameters
7.5B
Published
Dec 20, 2021
XGLM-7.5B is an AI model developed by Meta AI and Facebook AI Research (United States and France), first published in December 2021. It works in the language domain, on tasks such as translation, question answering and language modeling/generation.
Training it took an estimated 2.3×10²² FLOP of compute (estimation method: operation counting,hardware). The model has 7,500,000,000 parameters. It was trained on roughly 500B datapoints. Training ran on 256 NVIDIA A100 for about 504 hours. The compute alone is estimated at $104K in 2023 dollars.
Access: Open weights (non-commercial). Its weights are openly available. The reference paper has 381 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Meta AI, Facebook AI Research
- Country of organization
- United States, France
- Domain
- Language
- Task
- Translation, Question answering, Language modeling/generation
- Training compute
- 2.3×10²² FLOP
- Compute estimation method
- Operation counting, Hardware
- Parameters
- 7,500,000,000
- Dataset size
- 500B
- Training hardware
- NVIDIA A100
- Chips used
- 256
- Training time
- 504 h
- Chip-hours
- 129K
- Training power draw
- 206.3 kW
- Training cost (2023 USD)
- $104K
- Model accessibility
- Open weights (non-commercial)
- Open weights
- Yes
- Citations
- 381
- 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