HunyuanVideo 13B on Apple M1 Max (64 GB)

Can the Apple M1 Max (64 GB) run HunyuanVideo 13B?

Barely: it runs very slowly

Very slow. At Q4 GGUF it needs about 38.5 GB of 48.0 GB usable and takes about 7.2 h per clip.

Best precision: Q4 GGUF
Memory mode: Everything on GPU
Time per clip: 7.2 h
Output: 1280×720, 129 frames, 50 steps

Best app to run it on the Apple M1 Max (64 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 HunyuanVideo 13B 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 HunyuanVideo 13B

Recommended for the Apple M1 Max (64 GB): q4_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 q4_gguf (Q4_K_S) file (opens in a new tab)

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 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 66Good quality (B) · 66 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.: How capable the model itself is at Q4 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 M1 Max (64 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.	30.1 / 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.	1.3 / 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	71.4 / 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 Apple M1 Max (64 GB)

Quant	Memory needed	Available	Speed	Memory mode	Runs	Quality	Download
`FP16`	31.2 GB	48.0 GB	7.8 h	Sequential CPU offload	Very slowCPU offload	72Great quality (A) · 72 of 100: how capable the model is at FP16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`FP8`	43.7 GB	48.0 GB	5.4 h	Everything on GPU	Very slowtight fit	70Great quality (A) · 70 of 100: how capable the model is at FP8, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`Q8 GGUF`	44.6 GB	48.0 GB	6.9 h	Everything on GPU	Very slowtight fit	71Great quality (A) · 71 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4 GGUF`	38.5 GB	48.0 GB	7.2 h	Everything on GPU	Very slow	66Good quality (B) · 66 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)

Other hardware that runs it

72Great quality (A) · 72 of 100: how capable the model is at FP16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell FP16 · 29.3 min · Slow
70Great quality (A) · 70 of 100: how capable the model is at FP8, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 FP8 · 39.1 min · Slow (CPU offload)
72Great quality (A) · 72 of 100: how capable the model is at FP16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GH200 Grace Hopper (96 GB GPU) FP16 · 27.9 min · Slow
72Great quality (A) · 72 of 100: how capable the model is at FP16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H100 80GB SXM FP16 · 27.9 min · Slow
72Great quality (A) · 72 of 100: how capable the model is at FP16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H800 80GB SXM FP16 · 27.9 min · Slow
72Great quality (A) · 72 of 100: how capable the model is at FP16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H100 NVL FP16 · 30.2 min · Slow

Quick answers

How much memory does HunyuanVideo 13B need on the M1 Max 64GB?

At Q4 GGUF it needs about 38.5 GB. The M1 Max 64GB has 48.0 GB usable.

How long does HunyuanVideo 13B take on the M1 Max 64GB?

About 7.2 h per clip at Q4 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.