Can I run NVIDIA-Nemotron-3-Super-120B-A12B-BF16 on an NVIDIA H100?
No
Even its smallest file (4-bit (estimate), 69.5 GB) is more than an NVIDIA H100 can hold (72.0 GB usable): it needs 1 of them.
Files and context on NVIDIA H100
Each file of NVIDIA-Nemotron-3-Super-120B-A12B-BF16 (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 | 247 GB | Doesn't fit | — | — |
| 4-bit (estimate) | 69.5 GB | Doesn't fit | — | — |