Model Anatomy See what's inside open-weight AI models

Can I run NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUF on a Mac with 192 GB?

Yes, just

Its Q8_0 file (132 GB) fits in the 144 GB a Mac with 192 GB can use, with room for ≈ 1M tokens of context.

Full analysis of NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUF Everything that runs on Mac with 192 GB Get the Q8_0 file on Hugging Face
llama-server -hf unsloth/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUF:Q8_0

Files and context on Mac with 192 GB

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.

FileSizeOn Mac with 192 GB Context (16-bit)Context (8-bit)
Q8_0132 GBTight1M1M
UD-Q6_K_XL121 GBTight1M1M
UD-Q5_K_XL111 GBFits1M1M
UD-Q4_K_XL86.9 GBFits1M1M
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP477.7 GBFits1M1M
UD-Q3_K_XL65.8 GBFits1M1M
UD-IQ3_XXS59.8 GBFits1M1M
UD-Q2_K_XL57.8 GBFits1M1M
UD-IQ2_M55.9 GBFits1M1M
UD-IQ2_XXS51.1 GBFits1M1M
UD-IQ1_M46.1 GBFits1M1M

NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUF on other hardware

Popular models that run on Mac with 192 GB

Assumes 75% of the Mac's memory is usable (macOS's default limit for the GPU; it can be raised) and at least 4K tokens of context for one conversation, with the context cache in 16-bit unless noted. Fits leaves at least 20% of that memory for context; Tight leaves less.