granite 4.2 30b
29.3B parameters · 128k context · Apache 2.0 · released 2026-08-25
chatcodingagenticreasoning
What to run it on in India
Fully in memory at 64k context, priced at retailers today.
Nothing we price holds this model fully in memory.
All hardware that runs it
Everything we price, best value first. Two cards split the model by layers.
Nothing we price can run it at this context.
Memory needed
Weights, KV cache and runtime buffers at each context length (KV cache at fp16).
| Quant | File |
|---|
Run it
Copy a command for the runtime you use.
No published builds to run yet.
Notes
Native context is 128K; the card also claims a long-context extension to 512K, but all serving examples use 131072. The card recommends a vLLM reasoning parser that needs vLLM v0.20 or later (SGLang v0.5.18+ also works), with temperature=1.0 and top_p=0.95 required.
Questions
- What licence is granite 4.2 30b released under?
- Apache 2.0, which allows commercial use.