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

Can I run Kimi-K3 on an NVIDIA H100?

No

Even its smallest file (As published, 1.56 TB) is more than an NVIDIA H100 can hold (72.0 GB usable): it needs more than 8 of them.

Full analysis of Kimi-K3 Everything that runs on NVIDIA H100

Files and context on NVIDIA H100

Each file of Kimi-K3 (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 H100 Context (16-bit)Context (8-bit)
As published1.56 TBDoesn't fit——

Kimi-K3 on other hardware

Popular models that run on NVIDIA H100

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.