Nex N2.6 (321B-A18B) on Apple M3 Ultra (512 GB)

Can the Apple M3 Ultra (512 GB) run Nex N2.6 (321B-A18B)?

Yes, it runs great

Runs great. At Q4_K_M it needs about 227 GB of 384 GB usable, with an estimated speed of 41.4 tok/s.

Best quant: Q4_K_M
Generation speed: 41.4 tok/s
Prompt processing: 978 tok/s
First token (1K prompt): 1.0 s
Largest safe context: 1,024K

Best app to run it on the Apple M3 Ultra (512 GB)

On macOS

LM Studio

Desktop app · runs on llama.cpp, MLX

Point-and-click: search, download and chat in one window.

Open Nex N2.6 (321B-A18B) in LM Studio

llama.cpp Usually the first to support new model architectures.
Ollama Runs the Hugging Face GGUF with ollama run hf.co/…

Want an agent? Nex N2.6 (321B-A18B) supports tool use, so you can pair a llama.cpp or MLX LM server with one of these. Apps that run on this computer come first.

Coding agents

Personal assistants

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download Nex N2.6 (321B-A18B)

Recommended for the Apple M3 Ultra (512 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 files (opens in a new tab)

huggingface.co/bartowski/Nex-N2.6-GGUF (opens in a new tab)

ollama run hf.co/bartowski/Nex-N2.6-GGUF

Original weights · Hugging Face

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

huggingface.co/nex-agi/Nex-N2.6 (opens in a new tab)

No sign-in needed.

Links checked 3 hours ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 92Excellent quality (A+) · 92 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q4_K_M, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs great: How well it runs on the Apple M3 Ultra (512 GB): speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	41.5 / 45
Memory fitFull marks when the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.	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.	13.7 / 15
Match score	95.1 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the Apple M3 Ultra (512 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	160 GB	384 GB	63.4 tok/s	Runs great	67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q3_K_M`	189 GB	384 GB	51.7 tok/s	Runs great	81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q4_K_M`	227 GB	384 GB	41.4 tok/s	Runs great	92Excellent quality (A+) · 92 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q5_K_M`	260 GB	384 GB	34.9 tok/s	Runs great	94Excellent quality (A+) · 94 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q6_K`	295 GB	384 GB	29.8 tok/s	Runs well	96Excellent quality (A+) · 96 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q8_0`	372 GB	384 GB	22.4 tok/s	Runs welltight fit	97Excellent quality (A+) · 97 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`F16`	674 GB	384 GB	—	Won't run	97Excellent quality (A+) · 97 of 100: how capable the model is at F16, whatever it runs on. Match score 13/100 (quality, fit, speed and memory use) sets the ranking.	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

81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (256 GB) Q3_K_M · 51.7 tok/s · Runs well (tight fit)
67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. Apple M2 Ultra (192 GB) Q2_K · 62.2 tok/s · Runs well (tight fit)
96Excellent quality (A+) · 96 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 98/100 (quality, fit, speed and memory use) sets the ranking. Apple M5 Ultra (512 GB) Q6_K · 41.6 tok/s · Runs great
94Excellent quality (A+) · 94 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 97/100 (quality, fit, speed and memory use) sets the ranking. AMD Instinct MI350X Q5_K_M · 165 tok/s · Runs great
92Excellent quality (A+) · 92 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. AMD Instinct MI325X Q4_K_M · 161 tok/s · Runs great
92Excellent quality (A+) · 92 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip Q4_K_M · 184 tok/s · Runs great

Quick answers

How much memory does Nex N2.6 (321B-A18B) need on the M3 Ultra 512GB?

At Q4_K_M it needs about 227 GB. The M3 Ultra 512GB has 384 GB usable.

How fast is Nex N2.6 (321B-A18B) on the M3 Ultra 512GB?

About 41.4 tok/s at Q4_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Nex N2.6 (321B-A18B) should I use on the M3 Ultra 512GB?

Q4_K_M. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

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.