Can the AMD Radeon AI PRO R9600D run Qwen-Image?

Barely: it runs very slowly (encoder in RAM)

Very slow (encoder in RAM). At FP8 it needs about 26.8 GB of 32.0 GB usable and takes about 3.1 min per image.

Best precision: FP8
Memory mode: Text encoder offloaded
Time per image: 3.1 min
Output: 1328×1328, 50 steps

Best app to run it on the AMD Radeon AI PRO R9600D

On Windows

ComfyUI

Desktop app · runs on PyTorch (ComfyUI), GGUF via ComfyUI-GGUF

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

Get ComfyUI

On Linux

ComfyUI

Desktop app · runs on PyTorch (ComfyUI), GGUF via ComfyUI-GGUF

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

Get ComfyUI

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

Original weights · Hugging Face

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

huggingface.co/Qwen/Qwen-Image (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 7 minutes ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 86Excellent quality (A+) · 86 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.: How capable the model itself is at FP8, 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 slowencoder in RAM: How well it runs on the AMD Radeon AI PRO R9600D: 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.	38.8 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	20.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	3.5 / 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	77.3 / 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 AMD Radeon AI PRO R9600D

Quant	Memory needed	Available	Speed	Memory mode	Runs	Quality	Download
`FP16`	20.4 GB	32.0 GB	4.3 min	Sequential CPU offload	Very slowCPU offload	88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`FP8`	26.8 GB	32.0 GB	3.1 min	Text encoder offloaded	Very slowencoder in RAM	86Excellent quality (A+) · 86 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)

Other hardware that runs it

88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell FP16 · 66 s · Slow
86Excellent quality (A+) · 86 of 100: how capable the model is at FP8, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 FP8 · 71 s · Slow (encoder in RAM)
86Excellent quality (A+) · 86 of 100: how capable the model is at FP8, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 FP8 · 1.8 min · Slow (CPU offload)
86Excellent quality (A+) · 86 of 100: how capable the model is at FP8, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX FP8 · 2.0 min · Slow (CPU offload)
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GH200 Grace Hopper (96 GB GPU) FP16 · 63 s · Slow
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 85/100 (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 need on the AI PRO R9600D 32GB?

At FP8 it needs about 26.8 GB. The AI PRO R9600D 32GB has 32.0 GB usable.

How long does Qwen-Image take on the AI PRO R9600D 32GB?

About 3.1 min per image at FP8 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.