Nemotron 3 Nano 30B-A3B on NVIDIA GeForce RTX 4070 SUPER

Can the NVIDIA GeForce RTX 4070 SUPER run Nemotron 3 Nano 30B-A3B?

64 pts

Yes, with part of the model in system RAM

Runs with offload. At Q2_K it needs about 13.9 GB of 12.0 GB usable, with an estimated speed of 73.4 tok/s.

Best quant: Q2_K
Generation speed: 73.4 tok/s
Prompt processing: 6,541 tok/s
First token (1K prompt): 0.3 s
Largest safe context: —

Download Nemotron 3 Nano 30B-A3B

Quickest · Ollama

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

ollama run nemotron-3-nano:30b

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.

huggingface.co/ggml-org/NVIDIA-Nemotron-3-Nano-30B-A3B-GGUF (opens in a new tab)

ollama run hf.co/ggml-org/NVIDIA-Nemotron-3-Nano-30B-A3B-GGUF

Original weights · Hugging Face

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

huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-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 7 days ago against Hugging Face, Ollama and GitHub.

How the B 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.	24.3 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.	10.0 / 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	64.3 / 100	64 ptsGood (B) · 64 of 100 points: Model quality 24.3/45, Memory fit 10.0/25, 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 GeForce RTX 4070 SUPER

Quant	Memory needed	Available	Speed	Fit	Grade · points	Download
`Q2_K`	13.9 GB	12.0 GB	73.4 tok/s	Runs with offload	64 ptsGood (B) · 64 of 100 points: Model quality 24.3/45, Memory fit 10.0/25, Speed 15.0/15, Memory use 15.0/15	GGUF files (opens in a new tab)
`Q3_K_M`	16.7 GB	12.0 GB	38.1 tok/s	Heavy offload	62 ptsGood (B) · 62 of 100 points: Model quality 29.1/45, Memory fit 4.0/25, Speed 14.6/15, Memory use 15.0/15	GGUF files (opens in a new tab)
`Q4_K_M`	20.5 GB	12.0 GB	22.7 tok/s	Heavy offload	63 ptsGood (B) · 63 of 100 points: Model quality 32.9/45, Memory fit 4.0/25, Speed 11.3/15, Memory use 15.0/15	GGUF (opens in a new tab)
`Q5_K_M`	23.7 GB	12.0 GB	16.5 tok/s	Heavy offload	62 ptsGood (B) · 62 of 100 points: Model quality 33.6/45, Memory fit 4.0/25, Speed 9.6/15, Memory use 15.0/15	GGUF files (opens in a new tab)
`Q6_K`	27.1 GB	12.0 GB	12.7 tok/s	Heavy offload	61 ptsGood (B) · 61 of 100 points: Model quality 34.3/45, Memory fit 4.0/25, Speed 8.4/15, Memory use 15.0/15	GGUF files (opens in a new tab)
`Q8_0`	34.7 GB	12.0 GB	—	Won't run	10 ptsWon't run (F) · 10 of 100 points: Model quality 10.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF (opens in a new tab)
`F16`	64.4 GB	12.0 GB	—	Won't run	10 ptsWon't run (F) · 10 of 100 points: Model quality 10.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF (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

89 ptsExcellent (S) · 89 of 100 points: Model quality 34.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 Apple M4 Max (64 GB) Q8_0 · 42.0 tok/s
89 ptsExcellent (S) · 89 of 100 points: Model quality 34.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA RTX PRO 6000 Blackwell F16 · 73.7 tok/s
88 ptsExcellent (S) · 88 of 100 points: Model quality 34.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.6/15 Apple M1 Max (64 GB) Q6_K · 41.9 tok/s
88 ptsExcellent (S) · 88 of 100 points: Model quality 33.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5090 Q5_K_M · 260 tok/s
87 ptsExcellent (S) · 87 of 100 points: Model quality 32.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.6/15 Apple M4 Pro (48 GB) Q4_K_M · 41.2 tok/s
86 ptsExcellent (S) · 86 of 100 points: Model quality 32.9/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 AMD Radeon RX 7900 XTX Q4_K_M · 145 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.