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

Can I run gemma-2-9b-it-AWQ-INT4 on an NVIDIA B200?

Yes

Its published weights (6.16 GB) fit in the 162 GB an NVIDIA B200 can use, with room for ≈ 8K tokens of context.

Full analysis of gemma-2-9b-it-AWQ-INT4 Everything that runs on NVIDIA B200 Get the weights on Hugging Face
hf download hugging-quants/gemma-2-9b-it-AWQ-INT4

Files and context on NVIDIA B200

Each file of gemma-2-9b-it-AWQ-INT4 (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 published6.16 GBFits8K8K
4-bit (estimate)5.20 GBFits8K8K

gemma-2-9b-it-AWQ-INT4 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.