IBM is releasing its Granite 4.2 language models in 3B, 8B, and 30B sizes, trained on about 15 trillion tokens with a context window of up to 512,000 tokens. The larger models use "agentic RL" training to learn tool use and code execution on their own. All models are available under the Apache 2.0 license.

A Blog post by IBM Granite on Hugging Face

IBM’s new open Granite models are designed for agentic AI, combining reasoning, tool use, coding, instruction following, and speech capabilities.