Can the Apple M2 Max (96 GB) run Qwen-Image 2512?

Barely: it runs very slowly

Very slow. At Q8 GGUF it needs about 36.5 GB of 72.0 GB usable and takes about 12.7 min per image.

Best precision: Q8 GGUF
Memory mode: Everything on GPU
Time per image: 12.7 min
Output: 1328×1328, 50 steps

Best app to run it on the Apple M2 Max (96 GB)

On macOS

Draw Things

Desktop app · runs on Draw Things (Metal FlashAttention)

Native Mac app with its own fast Metal engine and quantized downloads.

Open Qwen-Image 2512 in Draw Things

ComfyUI Runs this model with built-in or popular custom nodes; GGUF files load with ComfyUI-GGUF.
SwarmUI

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 Qwen-Image 2512

Recommended for the Apple M2 Max (96 GB): q8_gguf. Every other precision has its own download link in the table below.

Quantized files · GGUF for ComfyUI

Smaller GGUF versions for ComfyUI (with the ComfyUI-GGUF node). No sign-in needed; the model’s license still applies.

Download the q8_gguf (Q8_0) file (opens in a new tab)

huggingface.co/unsloth/Qwen-Image-2512-GGUF (opens in a new tab)

Original weights · Hugging Face

Full-precision files from Alibaba, for fine-tuning, vLLM, Transformers, Diffusers or ComfyUI.

huggingface.co/Qwen/Qwen-Image-2512 (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Alibaba. The weights themselves download from Hugging Face.

github.com/QwenLM/Qwen-Image (opens in a new tab)

git clone https://github.com/QwenLM/Qwen-Image

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

How it’s rated

Quality 89Excellent quality (A+) · 89 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q8 GGUF, 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 Very slow: How well it runs on the Apple M2 Max (96 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.	40.1 / 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.	1.7 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	11.7 / 15
Match score	78.5 / 100

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

Every precision on the Apple M2 Max (96 GB)

Quant	Memory needed	Available	Speed	Memory mode	Runs	Quality	Download
`FP16`	63.8 GB	72.0 GB	11.0 min	Everything on GPU	Very slowtight fit	90Excellent quality (A+) · 90 of 100: how capable the model is at FP16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`FP8`	35.1 GB	72.0 GB	9.9 min	Everything on GPU	Very slow	88Excellent quality (A+) · 88 of 100: how capable the model is at FP8, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`Q8 GGUF`	36.5 GB	72.0 GB	12.7 min	Everything on GPU	Very slow	89Excellent quality (A+) · 89 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4 GGUF`	26.9 GB	72.0 GB	13.2 min	Everything on GPU	Very slow	83Great quality (A) · 83 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)

Other hardware that runs it

90Excellent quality (A+) · 90 of 100: how capable the model is at FP16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell FP16 · 66 s · Slow
83Great quality (A) · 83 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q4 GGUF · 1.5 min · Slow
83Great quality (A) · 83 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q4 GGUF · 1.9 min · Slow (encoder in RAM)
83Great quality (A) · 83 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q4 GGUF · 2.1 min · Slow (encoder in RAM)
90Excellent quality (A+) · 90 of 100: how capable the model is at FP16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GH200 Grace Hopper (96 GB GPU) FP16 · 63 s · Slow
90Excellent quality (A+) · 90 of 100: how capable the model is at FP16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H100 80GB SXM FP16 · 63 s · Slow

Quick answers

How much memory does Qwen-Image 2512 need on the M2 Max 96GB?

At Q8 GGUF it needs about 36.5 GB. The M2 Max 96GB has 72.0 GB usable.

How long does Qwen-Image 2512 take on the M2 Max 96GB?

About 12.7 min per image at Q8 GGUF and default settings, an estimate scaled from a reference timing by this hardware’s compute speed.

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.