26 August 2026
IBM releases Granite 4.2 language models in three sizes
First reported
Deep Learning Weekly ran this on , 5 days before the other 2 sources picked it up.
- IBM released three Granite 4.2 models with 3 billion, 8 billion, and 30 billion parameters, trained on 15 trillion tokens and supporting up to 512,000 token context windows.
- The 8B and 30B variants learn to use tools, write code, and search the web by training in real sandbox environments rather than on static instructions.
Where they differ
Reported by The Decoder