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

Can I run ESFT-token-intent-lite on an NVIDIA H200?

Yes

Its published weights (3.20 GB) fit in the 127 GB an NVIDIA H200 can use, with room for an unknown amount of context.

Full analysis of ESFT-token-intent-lite Everything that runs on NVIDIA H200 Get the weights on Hugging Face
hf download deepseek-ai/ESFT-token-intent-lite

Files and context on NVIDIA H200

Each file of ESFT-token-intent-lite (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 H200 Context (16-bit)Context (8-bit)
As published3.20 GBFitsnot knownnot known
4-bit (estimate)900 MBFitsnot knownnot known

ESFT-token-intent-lite on other hardware

Popular models that run on NVIDIA H200

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.