Can I run K2-Horizon-MoVA-36B-A4B on an NVIDIA H100?
Probably, at 4-bit
The published weights are too big, but a 4-bit version (about 21.1 GB) would fit, with room for ≈ 253K tokens of context. The site hasn't analyzed a GGUF of K2-Horizon-MoVA-36B-A4B yet.
Files and context on NVIDIA H100
Each file of K2-Horizon-MoVA-36B-A4B (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.
| File | Size | On NVIDIA H100 | Context (16-bit) | Context (8-bit) |
|---|---|---|---|---|
| As published | 74.9 GB | Doesn't fit | — | — |
| BF16 | 74.9 GB | Doesn't fit | — | — |