Can I run Raon-1-mini-preview on an NVIDIA H100?
Yes
Its published weights (32.7 GB) fit in the 72.0 GB an NVIDIA H100 can use, with room for an unknown amount of context.
Full analysis of Raon-1-mini-preview
Everything that runs on NVIDIA H100
Get the weights on Hugging Face
hf download KRAFTON/Raon-1-mini-previewFiles and context on NVIDIA H100
Each file of Raon-1-mini-preview (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 | 32.7 GB | Fits | not known | not known |
| raon-1-mini-preview-Q8_0 | 30.7 GB | Fits | not known | not known |
| Q6_K | 25.8 GB | Fits | not known | not known |
| Q5_K_M | 22.2 GB | Fits | not known | not known |
| Q4_K_M | 19.7 GB | Fits | not known | not known |
| IQ4_XS | 16.1 GB | Fits | not known | not known |