on

Can the Apple M2 Max (96 GB) run HiDream-I1 Full?

83Great quality (A) · 83 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.

Barely: it runs very slowly

Very slow. At Q8 GGUF it needs about 34.9 GB of 72.0 GB usable and takes about 6.3 min per image.

Best precision
Q8 GGUF
Memory mode
Everything on GPU
Time per image
6.3 min
Output
1024×1024, 50 steps

Best app to run it on the Apple M2 Max (96 GB)

On macOS

Draw Things

Desktop app · runs on Draw Things (Metal FlashAttention)

  • Native Mac app with its own fast Metal engine and quantized downloads.

Open HiDream-I1 Full in Draw Things

  • ComfyUI Runs this model with built-in or popular custom nodes; GGUF files load with ComfyUI-GGUF.
  • SwarmUI

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 Full

Recommended for the Apple M2 Max (96 GB): q8_gguf. Every other precision has its own download link in the table below.

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.

Download the q8_gguf (Q8_0) file (opens in a new tab)

huggingface.co/city96/HiDream-I1-Full-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-Full (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 2 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 83Great quality (A) · 83 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.
How capable the model itself is at Q8 GGUF, 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 Very slow
How well it runs on the Apple M2 Max (96 GB): 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.37.4 / 45
Memory fitFull marks when the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.2.4 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.11.2 / 15
Match score76.1 / 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 Apple M2 Max (96 GB)

Quant Memory needed Available Speed Memory mode Runs Quality Download
FP16 64.4 GB 72.0 GB 5.5 min Everything on GPU Very slowtight fit 84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. Original weights (opens in a new tab)
FP8 33.7 GB 72.0 GB 5.0 min Everything on GPU Very slow 82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. Original weights (opens in a new tab)
Q8 GGUF 34.9 GB 72.0 GB 6.3 min Everything on GPU Very slow 83Great quality (A) · 83 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q4 GGUF 26.9 GB 72.0 GB 6.6 min Everything on GPU Very slow 78Great quality (A) · 78 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 26.2 GB 72.0 GB 6.1 min Everything on GPU Very slow 78Great quality (A) · 78 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 Full need on the M2 Max 96GB?

At Q8 GGUF it needs about 34.9 GB. The M2 Max 96GB has 72.0 GB usable.

How long does HiDream-I1 Full take on the M2 Max 96GB?

About 6.3 min per image at Q8 GGUF 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?