Granite 3.1 8B

Training compute

5.8×10²³ FLOP

Parameters

8.1B

Published

Dec 18, 2024

Granite 3.1 8B is an AI model developed by IBM (United States), first published in December 2024. It works in the language domain, on tasks such as language modeling/generation, question answering and translation.

Training it took an estimated 5.8×10²³ FLOP of compute (estimation method: operation counting). The model has 8,100,000,000 parameters. It was trained on roughly 12T datapoints. Training ran on 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
Training compute: 5.8×10²³ FLOP
Compute estimation method: Operation counting
Parameters: 8,100,000,000
Dataset size: 12T
Training hardware: NVIDIA H100 SXM5 80GB
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Epoch confidence: Confident