IBM launches Granite 4.2 open-weight LLMs for local deployment

IBM has introduced Granite 4.2, a new family of open-weight large language models designed for download and self-hosting, available in 3B, 8B, and 30B parameter sizes. All variants feature a decoder-only architecture with a native 128,000-token context window. The 8B and 30B models received additional agentic reinforcement-learning training for tasks like terminal use, web search, and external tool interaction, while the 3B model supports tools without the same specialized training.