Can I run Inkling-Small-GGUF on an NVIDIA H200?
Yes, just
Its UD-Q3_K_XL file (120 GB) fits in the 127 GB an NVIDIA H200 can use, with room for ≈ 248K tokens of context.
Full analysis of Inkling-Small-GGUF
Everything that runs on NVIDIA H200
Get the UD-Q3_K_XL file on Hugging Face
llama-server -hf unsloth/Inkling-Small-GGUF:UD-Q3_K_XLFiles and context on NVIDIA H200
Each file of Inkling-Small-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.
| File | Size | On NVIDIA H200 | Context (16-bit) | Context (8-bit) |
|---|---|---|---|---|
| BF16 | 527 GB | Doesn't fit | — | — |
| UD-Q8_K_XL | 288 GB | Doesn't fit | — | — |
| Q8_0 | 280 GB | Doesn't fit | — | — |
| UD-Q6_K_XL | 240 GB | Doesn't fit | — | — |
| UD-Q6_K | 219 GB | Doesn't fit | — | — |
| UD-Q5_K_XL | 197 GB | Doesn't fit | — | — |
| UD-Q5_K_M | 196 GB | Doesn't fit | — | — |
| UD-Q5_K_S | 184 GB | Doesn't fit | — | — |
| UD-Q4_K_XL | 163 GB | Doesn't fit | — | — |
| UD-Q4_K_M | 163 GB | Doesn't fit | — | — |
| MXFP4_MOE | 158 GB | Doesn't fit | — | — |
| UD-Q4_K_S | 152 GB | Doesn't fit | — | — |
| UD-IQ4_NL | 130 GB | Doesn't fit | — | — |
| UD-IQ4_XS | 127 GB | Doesn't fit | — | — |
| UD-Q3_K_XL | 120 GB | Tight | 248K | 498K |
| UD-Q3_K_M | 119 GB | Tight | 254K | 511K |
| UD-IQ3_S | 107 GB | Tight | 660K | 1M |
| UD-IQ3_XXS | 97.9 GB | Fits | 984K | 1M |
| UD-Q2_K_XL | 87.9 GB | Fits | 1M | 1M |
| UD-IQ2_M | 82.4 GB | Fits | 1M | 1M |
| UD-IQ2_XXS | 82.3 GB | Fits | 1M | 1M |
| UD-IQ1_M | 78.8 GB | Fits | 1M | 1M |
| UD-IQ1_S | 74.8 GB | Fits | 1M | 1M |