Can I run Inkling-Small-GGUF on an RTX PRO 6000 Blackwell?
Yes, just
Its UD-IQ2_M file (82.4 GB) fits in the 86.4 GB an RTX PRO 6000 Blackwell can use, with room for ≈ 132K tokens of context. That file is under 3 bits per weight, so expect noticeably lower quality.
Full analysis of Inkling-Small-GGUF
Everything that runs on RTX PRO 6000 Blackwell
Get the UD-IQ2_M file on Hugging Face
llama-server -hf unsloth/Inkling-Small-GGUF:UD-IQ2_MFiles and context on RTX PRO 6000 Blackwell
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 RTX PRO 6000 Blackwell | 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 | Doesn't fit | — | — |
| UD-Q3_K_M | 119 GB | Doesn't fit | — | — |
| UD-IQ3_S | 107 GB | Doesn't fit | — | — |
| UD-IQ3_XXS | 97.9 GB | Doesn't fit | — | — |
| UD-Q2_K_XL | 87.9 GB | Doesn't fit | — | — |
| UD-IQ2_M | 82.4 GB | Tight | 132K | 267K |
| UD-IQ2_XXS | 82.3 GB | Tight | 138K | 278K |
| UD-IQ1_M | 78.8 GB | Tight | 255K | 513K |
| UD-IQ1_S | 74.8 GB | Tight | 394K | 790K |