Check my GPU

on

Can the Apple M2 Pro (32 GB) run Llama 3.1 Nemotron Nano 8B v1?

69 ptsGood (B) · 69 of 100 points: Model quality 23.1/45, Memory fit 25.0/25, Speed 12.2/15, Memory use 8.9/15

Yes, it runs well

Runs well. At Q4_K_M it needs about 8.3 GB of 21.4 GB usable, with an estimated speed of 26.3 tok/s.

Best quant
Q4_K_M
Generation speed
26.3 tok/s
Prompt processing
525 tok/s
First token (1K prompt)
2.0 s
Largest safe context
105K

Download Llama 3.1 Nemotron Nano 8B v1

Recommended for the Apple M2 Pro (32 GB): Q4_K_M. Every other quantization has its own download link in the table below.

Quantized files · GGUF

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

Download the Q4_K_M file (opens in a new tab)

huggingface.co/unsloth/Llama-3.1-Nemotron-Nano-8B-v1-GGUF (opens in a new tab)

ollama run hf.co/unsloth/Llama-3.1-Nemotron-Nano-8B-v1-GGUF:Q4_K_M

Original weights · Hugging Face

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

huggingface.co/nvidia/Llama-3.1-Nemotron-Nano-8B-v1 (opens in a new tab)

No sign-in needed.

Links checked 6 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.23.1 / 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.12.2 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.8.9 / 15
Total69.2 / 10069 ptsGood (B) · 69 of 100 points: Model quality 23.1/45, Memory fit 25.0/25, Speed 12.2/15, Memory use 8.9/15

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

Every quantization on the Apple M2 Pro (32 GB)

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 6.6 GB 21.4 GB 43.2 tok/s Runs well 64 ptsGood (B) · 64 of 100 points: Model quality 17.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.1/15 GGUF (opens in a new tab)
Q3_K_M 7.3 GB 21.4 GB 34.0 tok/s Runs well 67 ptsGood (B) · 67 of 100 points: Model quality 20.4/45, Memory fit 25.0/25, Speed 13.8/15, Memory use 7.9/15 GGUF (opens in a new tab)
Q4_K_M 8.3 GB 21.4 GB 26.3 tok/s Runs well 69 ptsGood (B) · 69 of 100 points: Model quality 23.1/45, Memory fit 25.0/25, Speed 12.2/15, Memory use 8.9/15 GGUF (opens in a new tab)
Q5_K_M 9.1 GB 21.4 GB 21.7 tok/s Runs well 69 ptsGood (B) · 69 of 100 points: Model quality 23.6/45, Memory fit 25.0/25, Speed 11.1/15, Memory use 9.8/15 GGUF (opens in a new tab)
Q6_K 10.0 GB 21.4 GB 18.3 tok/s Runs well 69 ptsGood (B) · 69 of 100 points: Model quality 24.1/45, Memory fit 25.0/25, Speed 10.1/15, Memory use 10.7/15 GGUF (opens in a new tab)
Q8_0 11.9 GB 21.4 GB 13.4 tok/s Runs well 70 ptsGood (B) · 70 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 8.7/15, Memory use 12.8/15 GGUF (UD-Q8_K_XL) (opens in a new tab)
F16 19.4 GB 21.4 GB 6.2 tok/s Tight fit 69 ptsGood (B) · 69 of 100 points: Model quality 24.3/45, Memory fit 24.0/25, Speed 5.9/15, Memory use 15.0/15 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

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.