HunyuanVideo 13B on NVIDIA GB10 (128 GB)

Can the NVIDIA GB10 (128 GB) run HunyuanVideo 13B?

73 pts

Yes, it runs well

Runs well. At FP16 it needs about 64.8 GB of 115 GB usable, with an estimated speed of 83.4 min.

Best precision: FP16
Memory mode: Everything on GPU
Time per clip: 83.4 min
Output: 1280×720, 129 frames, 50 steps

Download HunyuanVideo 13B

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/city96/HunyuanVideo-gguf (opens in a new tab)

Original weights · Hugging Face

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

huggingface.co/tencent/HunyuanVideo (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/HunyuanVideo (opens in a new tab)

git clone https://github.com/Tencent-Hunyuan/HunyuanVideo

Links checked 6 days ago against Hugging Face, Ollama and GitHub.

How the A grade is scored

Every result gets up to 100 points from four parts. The points decide the letter grade.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	32.4 / 45
Memory fitFull marks when everything sits in GPU or unified 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.	2.8 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	13.0 / 15
Total	73.2 / 100	73 ptsGreat (A) · 73 of 100 points: Model quality 32.4/45, Memory fit 25.0/25, Speed 2.8/15, Memory use 13.0/15

Grade scale: S 85+ · A 72+ · B 58+ · C 42+ · D 25+ · F under 25 points.

Every precision on the NVIDIA GB10 (128 GB)

Precision	Memory needed	Available	Time per output	Memory mode	Fit	Grade · points	Download
`FP16`	64.8 GB	115 GB	83.4 min	Everything on GPU	Runs well	73 ptsGreat (A) · 73 of 100 points: Model quality 32.4/45, Memory fit 25.0/25, Speed 2.8/15, Memory use 13.0/15	Original weights (opens in a new tab)
`FP8`	43.7 GB	115 GB	75.1 min	Everything on GPU	Runs well	68 ptsGood (B) · 68 of 100 points: Model quality 31.8/45, Memory fit 25.0/25, Speed 3.0/15, Memory use 8.8/15	Original weights (opens in a new tab)
`Q8 GGUF`	44.6 GB	115 GB	1.6 h	Everything on GPU	Runs well	68 ptsGood (B) · 68 of 100 points: Model quality 32.1/45, Memory fit 25.0/25, Speed 2.7/15, Memory use 8.9/15	GGUF (opens in a new tab)
`Q4 GGUF`	38.5 GB	115 GB	1.7 h	Everything on GPU	Runs well	65 ptsGood (B) · 65 of 100 points: Model quality 30.1/45, Memory fit 25.0/25, Speed 2.6/15, Memory use 7.7/15	GGUF (opens in a new tab)

Other hardware that runs it

77 ptsGreat (A) · 77 of 100 points: Model quality 32.4/45, Memory fit 25.0/25, Speed 4.8/15, Memory use 15.0/15 NVIDIA RTX PRO 6000 Blackwell FP16 · 29.3 min
75 ptsGreat (A) · 75 of 100 points: Model quality 32.4/45, Memory fit 25.0/25, Speed 3.0/15, Memory use 15.0/15 AMD Ryzen AI Max+ 395 (128 GB) FP16 · 76.8 min
74 ptsGreat (A) · 74 of 100 points: Model quality 32.4/45, Memory fit 25.0/25, Speed 1.7/15, Memory use 15.0/15 Apple M4 Max (128 GB) FP16 · 3.9 h
71 ptsGood (B) · 71 of 100 points: Model quality 30.1/45, Memory fit 25.0/25, Speed 1.5/15, Memory use 15.0/15 Apple M4 Max (64 GB) Q4 GGUF · 4.7 h
71 ptsGood (B) · 71 of 100 points: Model quality 30.1/45, Memory fit 25.0/25, Speed 1.3/15, Memory use 15.0/15 Apple M1 Max (64 GB) Q4 GGUF · 7.2 h

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.