Video models ·

Cosmos3-Super Image2Video (64B)

Backbone
64.0B
Native output
832×480, 189 frames
Default steps
50
License
openmdw-1.1
Released
2026-05

How to run it

Original weights · Hugging Face

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

huggingface.co/nvidia/Cosmos3-Super-Image2Video (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/nvidia/cosmos (opens in a new tab)

git clone https://github.com/nvidia/cosmos

Links checked 5 days ago against Hugging Face, Ollama and GitHub.

Apps that run Cosmos3-Super Image2Video (64B)

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 139 GB 138 GB 53.7 GB Original weights (opens in a new tab)

Components

Best hardware for Cosmos3-Super Image2Video (64B)

The least expensive GPU in our catalog that runs it without offloading is the NVIDIA RTX PRO 6000 Blackwell (launch price $8,565) 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 68/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Workstation EditionNVIDIA RTX PRO 6000 Blackwell FP16 53.7 GB / 96.0 GB 35.7 min SlowCPU offload
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA B200NVIDIA B200 FP16 139 GB / 180 GB 22.8 min Slow
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. AMD Instinct MI300XAMD Instinct MI300X FP16 139 GB / 192 GB 33.7 min Slow
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. AMD Instinct MI325XAMD Instinct MI325X FP16 139 GB / 256 GB 33.7 min Slow
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. Dell Pro Max with GB300NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip FP16 139 GB / 252 GB 38.4 min Slow
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. AMD Instinct MI350XAMD Instinct MI350X FP16 139 GB / 288 GB 38.5 min Slow
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H100 80GB SXMNVIDIA H100 80GB SXM FP16 53.7 GB / 80.0 GB 34.0 min SlowCPU offload
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H800 80GB SXMNVIDIA H800 80GB SXM FP16 53.7 GB / 80.0 GB 34.0 min SlowCPU offload
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H100 NVLNVIDIA H100 NVL FP16 53.7 GB / 94.0 GB 36.8 min SlowCPU offload
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GH200 Grace Hopper (96 GB GPU)NVIDIA GH200 Grace Hopper (96 GB GPU) FP16 53.7 GB / 96.0 GB 34.0 min SlowCPU offload

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?