OpenAI · Hugging Face
Granite 4.2 LLMs: How They're Rolled out
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
★ Tier-1 Source
That pipeline includes agentic RL, where the 8B and 30B models learn to act with tools inside real sandboxed environments.
Key facts
- Global batch size = prompts/step × generations/prompt (e.g. 256 × 16 = 4096 for RLVR)
- The non-agentic corpus consists of several major categories: instruction following (18.8%), coding (18.8%), math (14.6%), multilingual (7.0%), science (5.4%), reasoning (3.0%), and safety (0.8%)
- The agentic corpus covers a broad range of domains, including software engineering (SWE, 69%), tool calling (12.1%), terminal use (8.0%), math (3.5%), search (0.8%), and action (0.2%)
- To make this concrete, take RLVR, the first and longest-running stage: each step pairs 256 prompts with 16 sampled responses apiece for a 4,096-example batch, which the trainer consumes in a single
Summary
TL;DR: Granite 4.2 is their first family of dense, decoder-only reasoning LLMs, released in three sizes: 3B, 8B, and 30B. All Granite 4.2 models are released under the Apache 2.0 license. Granite 4.2 is the reasoning-focused release of the Granite language-model family. The three sizes ( 3B, 8B, and 30B ) share the same architectural design and follow the same training pipeline (pre-training from scratch, SFT, then multi-stage RL), each at its own scale. Granite 4.2 is also supported in SGLang, see the SGLang cookbook for a ready-to-serve recipe. The rest of this post walks through the build: architecture, pre-training, supervised fine-tuning, the multi-stage RL pipeline, and results. Granite 4.2 models are built on a decoder-only dense transformer architecture with the following core components:.