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

Can I run K2-Horizon-MoVA-36B-A4B-GGUF on an NVIDIA H100?

No

Even its smallest file (BF16, 74.9 GB) is more than an NVIDIA H100 can hold (72.0 GB usable): it needs 2 of them.

Full analysis of K2-Horizon-MoVA-36B-A4B-GGUF Everything that runs on NVIDIA H100

Files and context on NVIDIA H100

Each file of K2-Horizon-MoVA-36B-A4B-GGUF (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)
BF1674.9 GBDoesn't fit——

K2-Horizon-MoVA-36B-A4B-GGUF 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.