# Hugging Face — Granite 4.2 LLMs: How They're Built

- Company: Hugging Face (huggingface.co)
- Announced: 2026-08-25T15:14:14+00:00
- Category: new-model
- Subject: Platform
- Models affected: Granite 4.2, 3B, 8B, 30B
- License: Apache 2.0
- Context window: 512K tokens
- Source: https://huggingface.co/blog/ibm-granite/granite-4-2
- Record: https://forck.live/items/4407-granite-4-2-llms-how-they-re-built

IBM announced the Granite 4.2 family of reasoning LLMs in three sizes (3B, 8B, 30B), pre-trained from scratch on about 15T tokens, with a context window extended to 512K tokens, supervised fine-tuning on reasoning and agentic data, and released under the Apache 2.0 license.

## Evidence

Verbatim from https://huggingface.co/blog/ibm-granite/granite-4-2:

> Granite 4.2 is our first family of dense, decoder-only reasoning LLMs, released in three sizes: 3B, 8B, and 30B . Each model is pre-trained from scratch on roughly 15T tokens with a five-phase strategy that extends the context window to 512K tokens, supervised fine-tuned on chain-of-thought, reasoning, and agentic-trajectory data, then post-trained with a multi-stage reinforcement learning pipeline .

---

Record: https://forck.live/items/4407-granite-4-2-llms-how-they-re-built
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md