HunyuanImage 3.0 (80B-A13B) on NVIDIA GH200 Grace Hopper (96 GB GPU)

Can the NVIDIA GH200 Grace Hopper (96 GB GPU) run HunyuanImage 3.0 (80B-A13B)?

Yes, it runs well (tight fit)

Runs well (tight fit). At FP8 it needs about 86.9 GB of 96.0 GB usable, with an estimated speed of 38 s.

Best precision: FP8
Memory mode: Everything on GPU
Time per image: 38 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 6 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 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.: 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 Runs welltight fit: How well it runs on the NVIDIA GH200 Grace Hopper (96 GB GPU): 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.	39.7 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	23.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	7.7 / 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	85.4 / 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 NVIDIA GH200 Grace Hopper (96 GB GPU)

Quant	Memory needed	Available	Speed	Memory mode	Runs	Quality	Download
`FP16`	61.8 GB	96.0 GB	54 s	Sequential CPU offload	SlowCPU offload	90Excellent quality (A+) · 90 of 100: how capable the model is at FP16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`FP8`	86.9 GB	96.0 GB	38 s	Everything on GPU	Runs welltight fit	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.	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 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
88Excellent quality (A+) · 88 of 100: how capable the model is at FP8, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. AMD Ryzen AI Max+ 395 (128 GB) FP8 · 1.7 min · Slow (tight fit)

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.