Can the NVIDIA GB10 (128 GB) run HiDream-I1 Dev?

81 pts

Yes, it runs well

Runs well. At FP16 it needs about 64.4 GB of 115 GB usable, with an estimated speed of 35 s.

Best precision: FP16
Memory mode: Everything on GPU
Time per image: 35 s
Output: 1024×1024, 28 steps

Download HiDream-I1 Dev

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/HiDream-I1-Dev-gguf (opens in a new tab)

Original weights · Hugging Face

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

huggingface.co/HiDream-ai/HiDream-I1-Dev (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/HiDream-ai/HiDream-I1 (opens in a new tab)

git clone https://github.com/HiDream-ai/HiDream-I1

Links checked 5 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.	36.0 / 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.	8.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	12.9 / 15
Total	81.9 / 100	81 ptsGreat (A) · 81 of 100 points: Model quality 36.0/45, Memory fit 25.0/25, Speed 8.0/15, Memory use 12.9/15

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`	64.4 GB	115 GB	35 s	Everything on GPU	Runs well	81 ptsGreat (A) · 81 of 100 points: Model quality 36.0/45, Memory fit 25.0/25, Speed 8.0/15, Memory use 12.9/15	Original weights (opens in a new tab)
`FP8`	33.7 GB	115 GB	32 s	Everything on GPU	Runs well	75 ptsGreat (A) · 75 of 100 points: Model quality 35.3/45, Memory fit 25.0/25, Speed 8.4/15, Memory use 6.8/15	Original weights (opens in a new tab)
`Q8 GGUF`	34.9 GB	115 GB	41 s	Everything on GPU	Runs well	75 ptsGreat (A) · 75 of 100 points: Model quality 35.6/45, Memory fit 25.0/25, Speed 7.4/15, Memory use 7.0/15	GGUF (opens in a new tab)
`Q4 GGUF`	26.9 GB	115 GB	43 s	Everything on GPU	Runs well	71 ptsGood (B) · 71 of 100 points: Model quality 33.5/45, Memory fit 25.0/25, Speed 7.3/15, Memory use 5.4/15	GGUF (opens in a new tab)
`NF4`	26.2 GB	115 GB	39 s	Everything on GPU	Runs well	71 ptsGood (B) · 71 of 100 points: Model quality 33.5/45, Memory fit 25.0/25, Speed 7.6/15, Memory use 5.3/15	Original weights (opens in a new tab)

Other hardware that runs it

85 ptsExcellent (S) · 85 of 100 points: Model quality 33.5/45, Memory fit 25.0/25, Speed 12.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5090 NF4 · 16 s
84 ptsGreat (A) · 84 of 100 points: Model quality 36.0/45, Memory fit 25.0/25, Speed 8.3/15, Memory use 15.0/15 AMD Ryzen AI Max+ 395 (128 GB) FP16 · 33 s
82 ptsGreat (A) · 82 of 100 points: Model quality 35.3/45, Memory fit 25.0/25, Speed 14.2/15, Memory use 8.1/15 NVIDIA RTX PRO 6000 Blackwell FP8 · 11 s
82 ptsGreat (A) · 82 of 100 points: Model quality 35.3/45, Memory fit 20.0/25, Speed 11.8/15, Memory use 15.0/15 NVIDIA GeForce RTX 4090 FP8 · 16 s
81 ptsGreat (A) · 81 of 100 points: Model quality 35.3/45, Memory fit 20.0/25, Speed 11.2/15, Memory use 15.0/15 AMD Radeon RX 7900 XTX FP8 · 18 s

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.