HunyuanImage 3.0 (80B-A13B) on AMD Instinct MI350X

Can the AMD Instinct MI350X run HunyuanImage 3.0 (80B-A13B)?

Yes, but slowly

Slow. At FP16 it needs about 170 GB of 288 GB usable and takes about 62 s per image.

Best precision: FP16
Memory mode: Everything on GPU
Time per image: 62 s
Output: 1024×1024, 50 steps

Download HunyuanImage 3.0 (80B-A13B)

Original weights · Hugging Face

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

huggingface.co/tencent/HunyuanImage-3.0 (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/Tencent-Hunyuan/HunyuanImage-3.0 (opens in a new tab)

git clone https://github.com/Tencent-Hunyuan/HunyuanImage-3.0

Links checked 7 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 90Excellent quality (A+) · 90 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.: 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 AMD Instinct MI350X: 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.	40.5 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	6.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	13.6 / 15
Match score	85.2 / 100

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

Every precision on the AMD Instinct MI350X

Quant	Memory needed	Available	Speed	Memory mode	Runs	Quality	Download
`FP16`	170 GB	288 GB	62 s	Everything on GPU	Slow	90Excellent quality (A+) · 90 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.	Original weights (opens in a new tab)
`FP8`	86.9 GB	288 GB	55 s	Everything on GPU	Slow	88Excellent quality (A+) · 88 of 100: how capable the model is at FP8, whatever it runs on. Match score 78/100 (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 FP8, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell FP8 · 40 s · Runs well (tight fit)
88Excellent quality (A+) · 88 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 H200 141GB SXM FP8 · 38 s · Runs well
88Excellent quality (A+) · 88 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. NVIDIA GH200 Grace Hopper (96 GB GPU) FP8 · 38 s · Runs well (tight fit)
88Excellent quality (A+) · 88 of 100: how capable the model is at FP8, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA B200 FP8 · 33 s · Runs well
88Excellent quality (A+) · 88 of 100: how capable the model is at FP8, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GB10 (128 GB) FP8 · 1.9 min · Slow
88Excellent quality (A+) · 88 of 100: how capable the model is at FP8, 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) FP8 · 2.0 min · Slow

Quick answers

How much memory does HunyuanImage 3.0 (80B-A13B) need on the AMD Instinct MI350X 288GB?

At FP16 it needs about 170 GB. The AMD Instinct MI350X 288GB has 288 GB usable.

How long does HunyuanImage 3.0 (80B-A13B) take on the AMD Instinct MI350X 288GB?

About 62 s per image at FP16 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.