Video models ·

Kandinsky 6.0 Pro (29B, video + audio)

Backbone
30.1B
Native output
864×480, 121 frames
Default steps
50
License
mit
Released
2026-10

How to run it

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 5 days ago against Hugging Face, Ollama and GitHub.

Apps that run Kandinsky 6.0 Pro (29B, video + audio)

Our pick for each kind of computer, assuming the model fits in its memory. Pick your own GPU or device in the Model Finder for an exact answer.

Mac (Apple silicon)

ComfyUI

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

Also good:

Windows PC, NVIDIA GPU

ComfyUI

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

Also good:

Linux, NVIDIA or AMD GPU

ComfyUI

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

Also good:

App Type Opens it as Systems Engine Start
ComfyUI Desktop app Built-in support macOSWindowsLinux PyTorch, GGUF via ComfyUI-GGUF Get ComfyUI
SwarmUI Desktop app Built-in support macOSWindowsLinux ComfyUI Get SwarmUI
SD.Next Desktop app Built-in support macOSWindowsLinux PyTorch Get SD.Next
Stability Matrix Desktop app Built-in support macOSWindowsLinux installs ComfyUI, Forge, InvokeAI, SwarmUI, SD.Next or Fooocus Get Stability Matrix

Which apps can open a model depends on the files published for it: GGUF for llama.cpp-based apps, MLX for Apple’s engine, the original weights for vLLM and SGLang. Compare every app.

Memory needed

Peak GPU memory at the native output size. Offloading moves the text encoder, or the whole pipeline, to system RAM between steps.

Precision Everything on GPU Text encoder offloaded Sequential offload Download
FP16 85.4 GB 68.6 GB 27.8 GB Original weights (opens in a new tab)

Components

Best hardware for Kandinsky 6.0 Pro (29B, video + audio)

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc Pro B70 (launch price $949) at FP16.

Quality Hardware Quant Memory Speed Runs
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 Workstation EditionNVIDIA RTX PRO 6000 Blackwell FP16 85.4 GB / 96.0 GB 35.9 min Slowtight 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 SXMNVIDIA H200 141GB SXM FP16 85.4 GB / 141 GB 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 NVLNVIDIA H200 NVL FP16 85.4 GB / 141 GB 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)NVIDIA GH200 Grace Hopper (96 GB GPU) FP16 85.4 GB / 96.0 GB 34.1 min Slowtight 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 NVLNVIDIA H100 NVL FP16 85.4 GB / 94.0 GB 37.0 min Slowtight 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 EditionNVIDIA RTX PRO 6000 Blackwell Server Edition FP16 85.4 GB / 96.0 GB 37.0 min Slowtight 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 Max-Q Workstation EditionNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition FP16 85.4 GB / 96.0 GB 39.5 min Slowtight fit
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA B200NVIDIA B200 FP16 85.4 GB / 180 GB 29.8 min Slow
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H100 80GB SXMNVIDIA H100 80GB SXM FP16 68.6 GB / 80.0 GB 35.8 min Slowtight fit · encoder in RAM
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H800 80GB SXMNVIDIA H800 80GB SXM FP16 68.6 GB / 80.0 GB 35.8 min Slowtight fit · encoder in RAM

Check it on your own hardware

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?