Nemotron 3 Nano 4B on Apple M5 Max (64 GB)

Can the Apple M5 Max (64 GB) run Nemotron 3 Nano 4B?

66 pts

Yes, it runs well

Runs well. At Q8_0 it needs about 8.8 GB of 48.0 GB usable, with an estimated speed of 83.2 tok/s.

Best quant: Q8_0
Generation speed: 83.2 tok/s
Prompt processing: 2,952 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 256K

Download Nemotron 3 Nano 4B

Recommended for the Apple M5 Max (64 GB): Q8_0. 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-nano:4b-q8_0

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 Q8_0 file (opens in a new tab)

huggingface.co/unsloth/NVIDIA-Nemotron-3-Nano-4B-GGUF (opens in a new tab)

ollama run hf.co/unsloth/NVIDIA-Nemotron-3-Nano-4B-GGUF:Q8_0

Original weights · Hugging Face

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

huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-4B-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.	22.5 / 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.	4.2 / 15
Total	66.7 / 100	66 ptsGood (B) · 66 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.2/15

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

Every quantization on the Apple M5 Max (64 GB)

Quant	Memory needed	Available	Speed	Fit	Grade · points	Download
`Q2_K`	6.2 GB	48.0 GB	268 tok/s	Runs well	58 ptsGood (B) · 58 of 100 points: Model quality 15.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.0/15	GGUF (UD-Q2_K_XL) (opens in a new tab)
`Q3_K_M`	6.5 GB	48.0 GB	211 tok/s	Runs well	62 ptsGood (B) · 62 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.1/15	GGUF (opens in a new tab)
`Q4_K_M`	7.0 GB	48.0 GB	163 tok/s	Runs well	64 ptsGood (B) · 64 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.4/15	GGUF (opens in a new tab)
`Q5_K_M`	7.4 GB	48.0 GB	135 tok/s	Runs well	65 ptsGood (B) · 65 of 100 points: Model quality 21.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.6/15	GGUF (opens in a new tab)
`Q6_K`	7.8 GB	48.0 GB	113 tok/s	Runs well	66 ptsGood (B) · 66 of 100 points: Model quality 22.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.8/15	GGUF (opens in a new tab)
`Q8_0`	8.8 GB	48.0 GB	83.2 tok/s	Runs well	66 ptsGood (B) · 66 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.2/15	GGUF (opens in a new tab)
`F16`	12.5 GB	48.0 GB	38.4 tok/s	Runs well	68 ptsGood (B) · 68 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 14.7/15, Memory use 6.0/15	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

77 ptsGreat (A) · 77 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4060 Q8_0 · 42.8 tok/s
76 ptsGreat (A) · 76 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.7/15 NVIDIA GeForce RTX 4070 Ti SUPER F16 · 48.7 tok/s
76 ptsGreat (A) · 76 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.7/15 NVIDIA GeForce RTX 4080 SUPER F16 · 53.4 tok/s
76 ptsGreat (A) · 76 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.7/15 NVIDIA GeForce RTX 5070 Ti F16 · 65.0 tok/s
76 ptsGreat (A) · 76 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.7/15 NVIDIA GeForce RTX 5080 F16 · 69.6 tok/s
73 ptsGreat (A) · 73 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.7/15 Intel Arc B580 Q8_0 · 54.8 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.