Model Anatomy See what's inside open-weight AI models

Can I run granite-4.1-30b on an NVIDIA B200?

Yes

Its published weights (57.7 GB) fit in the 162 GB an NVIDIA B200 can use, with room for ≈ 128K tokens of context.

Full analysis of granite-4.1-30b Everything that runs on NVIDIA B200 Get the weights on Hugging Face
hf download ibm-granite/granite-4.1-30b

Files and context on NVIDIA B200

Each file of granite-4.1-30b (and of GGUF versions the site has analyzed), and how much context fits next to it, with the context cache in 16-bit or 8-bit.

FileSizeOn NVIDIA B200 Context (16-bit)Context (8-bit)
As published57.7 GBFits128K128K
4-bit (estimate)16.2 GBFits128K128K

granite-4.1-30b on other hardware

Popular models that run on NVIDIA B200

Assumes 90% of the card's memory is usable and at least 4K tokens of context for one conversation, with the context cache in 16-bit unless noted. Fits leaves at least 20% of that memory for context; Tight leaves less.