Granite-4.0-H-Micro

Training compute

3.1×10²³ FLOP

Parameters

3B

Published

Oct 2, 2025

Granite-4.0-H-Micro is an AI model developed by IBM (United States), first published in October 2025. It works in the language domain, on tasks such as language modeling/generation, question answering, text summarization and 3 more.

Training it took an estimated 3.1×10²³ FLOP of compute (estimation method: operation counting). The model has 3,000,000,000 parameters. Training ran on NVIDIA GB200.

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, Text summarization, Text classification, Retrieval-augmented generation, Code generation
Training compute: 3.1×10²³ FLOP
Compute estimation method: Operation counting
Parameters: 3,000,000,000
Training hardware: NVIDIA GB200
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Epoch confidence: Confident