on

Can the NVIDIA Quadro RTX 6000 run HiDream-I1 Dev?

78Great quality (A) · 78 of 100: how capable the model is at FP8, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.

Yes, but slowly (encoder in RAM)

Slow (encoder in RAM). At FP8 it needs about 20.1 GB of 24.0 GB usable and takes about 54 s per image.

Best precision
FP8
Memory mode
Text encoder offloaded
Time per image
54 s
Output
1024×1024, 28 steps

Best app to run it on the NVIDIA Quadro RTX 6000

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 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 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 78Great quality (A) · 78 of 100: how capable the model is at FP8, whatever it runs on. Match score 76/100 (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 Slowencoder in RAM
How well it runs on the NVIDIA Quadro RTX 6000: 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.35.3 / 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.6.4 / 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 score76.7 / 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 Quadro RTX 6000

Quant Memory needed Available Speed Memory mode Runs Quality Download
FP16 14.8 GB 24.0 GB 75 s Sequential CPU offload SlowCPU offload 80Great quality (A) · 80 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. Original weights (opens in a new tab)
FP8 20.1 GB 24.0 GB 54 s Text encoder offloaded Slowencoder in RAM 78Great quality (A) · 78 of 100: how capable the model is at FP8, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. Original weights (opens in a new tab)
Q8 GGUF 21.3 GB 24.0 GB 69 s Text encoder offloaded Slowtight fit · encoder in RAM 79Great quality (A) · 79 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q4 GGUF 13.3 GB 24.0 GB 72 s Text encoder offloaded Slowencoder in RAM 74Great quality (A) · 74 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
NF4 12.6 GB 24.0 GB 66 s Text encoder offloaded Slowencoder in RAM 74Great quality (A) · 74 of 100: how capable the model is at NF4, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. Original weights (opens in a new tab)

Other hardware that runs it

Quick answers

How much memory does HiDream-I1 Dev need on the NVIDIA Quadro RTX 6000 24GB?

At FP8 it needs about 20.1 GB. The NVIDIA Quadro RTX 6000 24GB has 24.0 GB usable.

How long does HiDream-I1 Dev take on the NVIDIA Quadro RTX 6000 24GB?

About 54 s 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.

Was this page helpful?