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

Can I run Victoria on an NVIDIA B300?

Yes

Its victoria-s410-bitexact file (155 GB) fits in the 259 GB an NVIDIA B300 can use, with room for ≈ 256K tokens of context.

Full analysis of Victoria Everything that runs on NVIDIA B300 Get the victoria-s410-bitexact file on Hugging Face
llama-server -hf rmonsurate/Victoria

Files and context on NVIDIA B300

Each file of Victoria (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 B300 Context (16-bit)Context (8-bit)
victoria-s410-bitexact155 GBFits256K256K
victoria-s410-bitexact-tbl8107 GBFits256K256K

Victoria on other hardware

Popular models that run on NVIDIA B300

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.