Granite 4.2 LLMs: How They're Built

Automated excerpt

These models are post-trained from Granite-4.1 base models. That pipeline includes agentic RL, where the 8B and 30B models learn to act with tools inside real sandboxed environments. Every model supports native tool calling. Foundational RL (verifiable rewards + skill boosters) runs for all sizes; the agentic RL block (SWE → Terminal → Search) runs for 8B and 30B only. Results Granite 4.2 was evaluated across agentic coding, general agentic and tool use, reasoning, chat and instruction following, and long context.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.