Can I run NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUF on an RTX PRO 6000 Blackwell?
Yes, just
Its NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4 file (77.7 GB) fits in the 86.4 GB an RTX PRO 6000 Blackwell can use, with room for ≈ 1018K tokens of context.
Full analysis of NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUF
Everything that runs on RTX PRO 6000 Blackwell
Get the NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4 file on Hugging Face
llama-server -hf unsloth/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUFFiles and context on RTX PRO 6000 Blackwell
Each file of NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-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) |
|---|---|---|---|---|
| Q8_0 | 132 GB | Doesn't fit | — | — |
| UD-Q6_K_XL | 121 GB | Doesn't fit | — | — |
| UD-Q5_K_XL | 111 GB | Doesn't fit | — | — |
| UD-Q4_K_XL | 86.9 GB | Doesn't fit | — | — |
| NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4 | 77.7 GB | Tight | 1018K | 1M |
| UD-Q3_K_XL | 65.8 GB | Fits | 1M | 1M |
| UD-IQ3_XXS | 59.8 GB | Fits | 1M | 1M |
| UD-Q2_K_XL | 57.8 GB | Fits | 1M | 1M |
| UD-IQ2_M | 55.9 GB | Fits | 1M | 1M |
| UD-IQ2_XXS | 51.1 GB | Fits | 1M | 1M |
| UD-IQ1_M | 46.1 GB | Fits | 1M | 1M |