Kandinsky 6.0 Pro (29B, video + audio) on Apple M3 Pro (36 GB)

Can the Apple M3 Pro (36 GB) run Kandinsky 6.0 Pro (29B, video + audio)?

No, it doesn’t fit

No. Kandinsky 6.0 Pro (29B, video + audio) needs about 27.8 GB even at FP16; the Apple M3 Pro (36 GB) has 24.1 GB usable.

Download Kandinsky 6.0 Pro (29B, video + audio)

Original weights · Hugging Face

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

huggingface.co/kandinskylab/Kandinsky-6.0-Pro-5s-Diffusers (opens in a new tab)

Free Hugging Face account needed: accept the license on the model page and the download starts right away.

Official repo · GitHub

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

github.com/kandinskylab/kandinsky-6 (opens in a new tab)

git clone https://github.com/kandinskylab/kandinsky-6

Links checked 6 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 11/100 (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 Won't run: How well it runs on the Apple M3 Pro (36 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.	11.9 / 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.	0.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	0.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	0.0 / 15
Match score	11.9 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

It doesn’t fit, so only a reduced share of the quality points counts and fit, speed and memory use score zero.

Every precision on the Apple M3 Pro (36 GB)

Quant	Memory needed	Available	Speed	Memory mode	Runs	Quality	Download
`FP16`	27.8 GB	24.1 GB	—	—	Won't run	88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Hardware that can run it

88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell FP16 · 35.9 min · Slow (tight fit)
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H200 141GB SXM FP16 · 34.1 min · Slow
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H200 NVL FP16 · 37.0 min · Slow
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GH200 Grace Hopper (96 GB GPU) FP16 · 34.1 min · Slow (tight fit)
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H100 NVL FP16 · 37.0 min · Slow (tight fit)
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Server Edition FP16 · 37.0 min · Slow (tight fit)

Models that do run on the Apple M3 Pro (36 GB)

83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. Bernini-R A14B (video generation + editing) FP8 · 2.2 h
86Excellent quality (A+) · 86 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. LTX-2.5 (22B, video + audio) FP8 · 20.6 min
70Great quality (A) · 70 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. Wan 2.2 S2V 14B (speech to video) Q4 GGUF · 3.9 h
74Great quality (A) · 74 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. HY-OmniWeaving (8.3B, unified video) FP8 · 1.6 h
68Good quality (B) · 68 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. Wan 2.1 I2V 14B 480P Q4 GGUF · 3.5 h

Quick answers

How much memory does Kandinsky 6.0 Pro (29B, video + audio) need on the M3 Pro 36GB?

Even at FP16 it needs about 27.8 GB; the M3 Pro 36GB has 24.1 GB usable.

What can the M3 Pro 36GB run instead?

Bernini-R A14B (video generation + editing), LTX-2.5 (22B, video + audio) and Wan 2.2 S2V 14B (speech to video) run best on it; the page lists more, each with its speed.

What hardware can run Kandinsky 6.0 Pro (29B, video + audio)?

NVIDIA RTX PRO 6000 Blackwell 96GB, NVIDIA H200 141GB SXM and NVIDIA H200 NVL 141GB run it; the page lists more, each with its 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.