Granite 20B

Training compute

3×10²³ FLOP

Parameters

20B

Published

May 31, 2024

Granite 20B is an AI model developed by IBM Research (United States), first published in May 2024. It works in the language domain, on tasks such as language modeling/generation.

Training it took an estimated 3×10²³ FLOP of compute (estimation method: operation counting). The model has 20,000,000,000 parameters. It was trained on roughly 2.5T datapoints.

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

Full record

Organization: IBM Research
Country of organization: United States
Domain: Language
Task: Language modeling/generation
Training compute: 3×10²³ FLOP
Compute estimation method: Operation counting
Parameters: 20,000,000,000
Dataset size: 2.5T
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Epoch confidence: Confident