Nemotron 3 Super 120B-A12B on NVIDIA RTX PRO 6000 Blackwell

Can the NVIDIA RTX PRO 6000 Blackwell run Nemotron 3 Super 120B-A12B?

92 pts

Yes, it runs well

Runs well. At Q4_K_M it needs about 80.9 GB of 96.0 GB usable, with an estimated speed of 91.7 tok/s.

Best quant: Q4_K_M
Generation speed: 91.7 tok/s
Prompt processing: 7,500 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 256K

Download Nemotron 3 Super 120B-A12B

Recommended for the NVIDIA RTX PRO 6000 Blackwell: Q4_K_M. Every other quantization has its own download link in the table below.

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

ollama run nemotron-3-super:120b-a12b-q4_K_M

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the Q4_K_M files (opens in a new tab)

huggingface.co/unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-GGUF (opens in a new tab)

ollama run hf.co/unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-GGUF

Original weights · Hugging Face

Full-precision files from NVIDIA, for fine-tuning, vLLM, Transformers.

huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from NVIDIA. The weights themselves download from Hugging Face.

github.com/NVIDIA-NeMo/Nemotron (opens in a new tab)

git clone https://github.com/NVIDIA-NeMo/Nemotron

NVIDIA’s Nemotron repo with recipes for the whole family.

Links checked 39 minutes ago against Hugging Face, Ollama and GitHub.

How the S grade is scored

Every result gets up to 100 points from four parts. The points decide the letter grade.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	37.6 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	15.0 / 15
Total	92.6 / 100	92 ptsExcellent (S) · 92 of 100 points: Model quality 37.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15

Grade scale: S 85+ · A 72+ · B 58+ · C 42+ · D 25+ · F under 25 points.

Every quantization on the NVIDIA RTX PRO 6000 Blackwell

Quant	Memory needed	Available	Speed	Fit	Grade · points	Download
`Q2_K`	54.9 GB	96.0 GB	151 tok/s	Runs well	80 ptsGreat (A) · 80 of 100 points: Model quality 27.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.2/15	GGUF (UD-Q2_K_XL) · folder (opens in a new tab)
`Q3_K_M`	66.0 GB	96.0 GB	118 tok/s	Runs well	88 ptsExcellent (S) · 88 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	GGUF · folder (opens in a new tab)
`Q4_K_M`	80.9 GB	96.0 GB	91.7 tok/s	Runs well	92 ptsExcellent (S) · 92 of 100 points: Model quality 37.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	GGUF · folder (opens in a new tab)
`Q5_K_M`	93.2 GB	96.0 GB	75.7 tok/s	Tight fit	92 ptsExcellent (S) · 92 of 100 points: Model quality 38.4/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15	GGUF · folder (opens in a new tab)
`Q6_K`	107 GB	96.0 GB	16.9 tok/s	Runs with offload	73 ptsGreat (A) · 73 of 100 points: Model quality 39.2/45, Memory fit 10.0/25, Speed 9.7/15, Memory use 15.0/15	GGUF · folder (opens in a new tab)
`Q8_0`	136 GB	96.0 GB	—	Won't run	11 ptsWon't run (F) · 11 of 100 points: Model quality 11.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF · folder (opens in a new tab)
`F16`	253 GB	96.0 GB	—	Won't run	11 ptsWon't run (F) · 11 of 100 points: Model quality 11.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF · folder (opens in a new tab) Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

90 ptsExcellent (S) · 90 of 100 points: Model quality 37.6/45, Memory fit 25.0/25, Speed 14.1/15, Memory use 14.0/15 Apple M2 Ultra (192 GB) Q4_K_M · 35.2 tok/s
88 ptsExcellent (S) · 88 of 100 points: Model quality 37.6/45, Memory fit 24.0/25, Speed 11.6/15, Memory use 15.0/15 Apple M4 Max (128 GB) Q4_K_M · 24.0 tok/s
87 ptsExcellent (S) · 87 of 100 points: Model quality 37.6/45, Memory fit 25.0/25, Speed 14.2/15, Memory use 11.0/15 Apple M3 Ultra (256 GB) Q4_K_M · 36.1 tok/s
86 ptsExcellent (S) · 86 of 100 points: Model quality 37.6/45, Memory fit 25.0/25, Speed 8.9/15, Memory use 15.0/15 NVIDIA GB10 (128 GB) Q4_K_M · 14.0 tok/s
84 ptsGreat (A) · 84 of 100 points: Model quality 37.6/45, Memory fit 24.0/25, Speed 8.0/15, Memory use 15.0/15 AMD Ryzen AI Max+ 395 (128 GB) Q4_K_M · 11.3 tok/s

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.