Nemotron Cascade 2 30B-A3B on Apple M3 Max (36 GB)

Can the Apple M3 Max (36 GB) run Nemotron Cascade 2 30B-A3B?

Yes, it runs well (tight fit)

Runs well (tight fit). At Q4_K_M it needs about 21.8 GB of 24.1 GB usable, with an estimated speed of 69.4 tok/s.

Best quant: Q4_K_M
Generation speed: 69.4 tok/s
Prompt processing: 2,179 tok/s
First token (1K prompt): 0.5 s
Largest safe context: 256K

Best app to run it on the Apple M3 Max (36 GB)

On macOS

LM Studio

Desktop app · runs on llama.cpp, MLX · use the MLX build

Runs the MLX build, typically 35–90% faster than GGUF for a model with 3.5B active parameters on Apple silicon.
Point-and-click: search, download and chat in one window.

Open Nemotron Cascade 2 30B-A3B in LM Studio

MLX LM Runs the MLX build, typically 35–90% faster than GGUF for a model with 3.5B active parameters on Apple silicon.
Unsloth Desktop Runs the MLX build, typically 35–90% faster than GGUF for a model with 3.5B active parameters on Apple silicon.

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 Nemotron Cascade 2 30B-A3B

Recommended for the Apple M3 Max (36 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/bartowski/nvidia_Nemotron-Cascade-2-30B-A3B-GGUF (opens in a new tab)

ollama run hf.co/bartowski/nvidia_Nemotron-Cascade-2-30B-A3B-GGUF:Q4_K_M

Original weights · Hugging Face

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

huggingface.co/nvidia/Nemotron-Cascade-2-30B-A3B (opens in a new tab)

No sign-in needed.

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

How it’s rated

Quality 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 88/100 (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 welltight fit: How well it runs on the Apple M3 Max (36 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.	34.2 / 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.	24.0 / 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
Match score	88.2 / 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 Max (36 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	15.2 GB	24.1 GB	102 tok/s	Runs great	56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	18.1 GB	24.1 GB	84.9 tok/s	Runs great	67Good quality (B) · 67 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	21.8 GB	24.1 GB	69.4 tok/s	Runs welltight fit	76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	25.0 GB	24.1 GB	50.4 tok/s	Runs wellover GPU memory limit	77Great quality (A) · 77 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	28.5 GB	24.1 GB	43.6 tok/s	Slowfar over GPU memory limit	79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	36.1 GB	24.1 GB	—	Won't run	80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	65.7 GB	24.1 GB	—	Won't run	80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking.	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

80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. Apple M1 Max (64 GB) Q8_0 · 49.8 tok/s · Runs great
80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (64 GB) Q8_0 · 63.6 tok/s · Runs great
80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell F16 · 89.6 tok/s · Runs great
79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Pro (48 GB) Q6_K · 47.4 tok/s · Runs great
77Great quality (A) · 77 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q5_K_M · 184 tok/s · Runs great
76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q4_K_M · 147 tok/s · Runs well (tight fit)

Quick answers

How much memory does Nemotron Cascade 2 30B-A3B need on the M3 Max 36GB?

At Q4_K_M it needs about 21.8 GB. The M3 Max 36GB has 24.1 GB usable.

How fast is Nemotron Cascade 2 30B-A3B on the M3 Max 36GB?

About 69.4 tok/s at Q4_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Nemotron Cascade 2 30B-A3B should I use on the M3 Max 36GB?

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.