Llama 4 Scout + ScaleRL

Parameters

109B

Published

Oct 15, 2025

Llama 4 Scout + ScaleRL is an AI model developed by Meta AI (United States), first published in October 2025. It works in the language domain, on tasks such as language modeling/generation, question answering and code generation.

Epoch AI has no training-compute estimate for this model. The model has 109,000,000,000 parameters. Training ran on 80 NVIDIA GB200.

Access: Unreleased. Its weights are not openly released. It is built on top of Llama 4 Scout. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Meta AI
Country of organization: United States
Domain: Language
Task: Language modeling/generation, Question answering, Code generation
Compute estimation method: Hardware
Parameters: 109,000,000,000
Training hardware: NVIDIA GB200
Chips used: 80
Chip-hours: 50K
Training power draw: 187.5 kW
Model accessibility: Unreleased
Open weights: No
Base model: Llama 4 Scout
Epoch confidence: Confident