Llama 3.3 70B

Training compute

6.9×10²⁴ FLOP

Parameters

70B

Published

Dec 6, 2024

Llama 3.3 70B is an AI model developed by Meta AI (United States), first published in December 2024. It works in the language domain, on tasks such as language modeling/generation, question answering, translation and code generation.

Training it took an estimated 6.9×10²⁴ FLOP of compute (estimation method: operation counting,hardware). The model has 70,000,000,000 parameters. It was trained on roughly 15T datapoints. Training ran on NVIDIA H100 SXM5 80GB.

Access: Open weights (restricted use). Its weights are openly available. 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, Translation, Code generation
Training compute: 6.9×10²⁴ FLOP
Compute estimation method: Operation counting, Hardware
Parameters: 70,000,000,000
Dataset size: 15T
Training hardware: NVIDIA H100 SXM5 80GB
Chip-hours: 7M
Model accessibility: Open weights (restricted use)
Open weights: Yes
Epoch confidence: Confident

Benchmark results

01

Epoch Capabilities Index

ECI Score

127.5