Granite 3.0 8B

Training compute

5.8×10²³ FLOP

Parameters

8.1B

Published

Oct 21, 2024

Granite 3.0 8B is an AI model developed by IBM (United States), first published in October 2024. It works in the language domain, on tasks such as language modeling/generation, question answering, translation and 3 more.

Training it took an estimated 5.8×10²³ FLOP of compute (estimation method: operation counting,hardware). The model has 8,100,000,000 parameters. It was trained on roughly 12T datapoints. Training ran on 256 NVIDIA H100 SXM5 80GB.

Access: Open weights (unrestricted). Its weights are openly available. Epoch AI rates the confidence of this record as confident.

Full record

Organization: IBM
Country of organization: United States
Domain: Language
Task: Language modeling/generation, Question answering, Translation, Text summarization, Text classification, Code generation
Training compute: 5.8×10²³ FLOP
Compute estimation method: Operation counting, Hardware
Parameters: 8,100,000,000
Dataset size: 12T
Training hardware: NVIDIA H100 SXM5 80GB
Chips used: 256
Chip-hours: 832.1K
Training power draw: 352.8 kW
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Epoch confidence: Confident