Qwen-Image 2.1 Turbo on Apple M3 Ultra (512 GB)

Can the Apple M3 Ultra (512 GB) run Qwen-Image 2.1 Turbo?

Yes, but slowly

Slow. At FP16 it needs about 46.7 GB of 384 GB usable, with an estimated speed of 49 s.

Best precision: FP16
Memory mode: Everything on GPU
Time per image: 49 s
Output: 2048×2048, 8 steps

Best app to run it on the Apple M3 Ultra (512 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 2.1 Turbo 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 2.1 Turbo

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.

huggingface.co/unsloth/Qwen-Image-2.1-Turbo-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-2.1-Turbo (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-2.1 (opens in a new tab)

git clone https://github.com/QwenLM/Qwen-Image-2.1

Links checked 1 day ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 89Excellent quality (A+) · 89 of 100: how capable the model is at FP16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at FP16, 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 Slow: 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.	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.	6.8 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	2.8 / 15
Match score	74.6 / 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 M3 Ultra (512 GB)

Quant	Memory needed	Available	Speed	Memory mode	Runs	Quality	Download
`FP16`	46.7 GB	384 GB	49 s	Everything on GPU	Slow	89Excellent quality (A+) · 89 of 100: how capable the model is at FP16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`FP8`	30.8 GB	384 GB	44 s	Everything on GPU	Slow	87Excellent quality (A+) · 87 of 100: how capable the model is at FP8, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`Q8 GGUF`	31.3 GB	384 GB	56 s	Everything on GPU	Slow	88Excellent quality (A+) · 88 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4 GGUF`	28.0 GB	384 GB	59 s	Everything on GPU	Slow	82Great quality (A) · 82 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)

Other hardware that runs it

87Excellent quality (A+) · 87 of 100: how capable the model is at FP8, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 FP8 · 8.7 s · Runs well (tight fit)
89Excellent quality (A+) · 89 of 100: how capable the model is at FP16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell FP16 · 8.5 s · Runs great
87Excellent quality (A+) · 87 of 100: how capable the model is at FP8, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 FP8 · 11 s · Runs well (tight fit · encoder in RAM)
89Excellent quality (A+) · 89 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. AMD Ryzen AI Max+ 395 (128 GB) FP16 · 22 s · Runs well
87Excellent quality (A+) · 87 of 100: how capable the model is at FP8, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX FP8 · 12 s · Runs well (tight fit · encoder in RAM)
89Excellent quality (A+) · 89 of 100: how capable the model is at FP16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX Spark N1X (6144-core GPU) (128 GB) FP16 · 26 s · Runs well

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.