Step-Video T2V (30B) on Apple M3 Ultra (256 GB)

Can the Apple M3 Ultra (256 GB) run Step-Video T2V (30B)?

Barely: it runs very slowly

Very slow. At FP16 it needs about 78.2 GB of 192 GB usable and takes about 3.6 h per clip.

Best precision: FP16
Memory mode: Everything on GPU
Time per clip: 3.6 h
Output: 992×544, 204 frames, 50 steps

Download Step-Video T2V (30B)

Original weights · Hugging Face

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

huggingface.co/stepfun-ai/stepvideo-t2v (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/stepfun-ai/Step-Video-T2V (opens in a new tab)

git clone https://github.com/stepfun-ai/Step-Video-T2V

Links checked 2 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 76Great quality (A) · 76 of 100: how capable the model is at FP16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at FP16, 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 M3 Ultra (256 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.	34.2 / 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.	1.8 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	9.4 / 15
Match score	70.4 / 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 M3 Ultra (256 GB)

Quant	Memory needed	Available	Speed	Memory mode	Runs	Quality	Download
`FP16`	78.2 GB	192 GB	3.6 h	Everything on GPU	Very slow	76Great quality (A) · 76 of 100: how capable the model is at FP16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`FP8`	46.8 GB	192 GB	3.3 h	Everything on GPU	Very slow	74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Other hardware that runs it

76Great quality (A) · 76 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. NVIDIA RTX PRO 6000 Blackwell FP16 · 37.9 min · Slow
76Great quality (A) · 76 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. NVIDIA GH200 Grace Hopper (96 GB GPU) FP16 · 36.0 min · Slow
76Great quality (A) · 76 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. NVIDIA H100 NVL FP16 · 39.0 min · Slow
76Great quality (A) · 76 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. NVIDIA RTX PRO 6000 Blackwell Server Edition FP16 · 39.0 min · Slow
74Great quality (A) · 74 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. NVIDIA H100 80GB SXM FP8 · 32.4 min · Slow
74Great quality (A) · 74 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. NVIDIA H800 80GB SXM FP8 · 32.4 min · Slow

Quick answers

How much memory does Step-Video T2V (30B) need on the M3 Ultra 256GB?

At FP16 it needs about 78.2 GB. The M3 Ultra 256GB has 192 GB usable.

How long does Step-Video T2V (30B) take on the M3 Ultra 256GB?

About 3.6 h per clip at FP16 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.