Video models ·

Cosmos-Predict2 14B Video2World

Backbone
14.0B
Native output
1280×704, 93 frames
Default steps
35
License
nvidia-open-model-license
Released
2025-06

How to run it

Original weights · Hugging Face

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

huggingface.co/nvidia/Cosmos-Predict2-14B-Video2World (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 NVIDIA. The weights themselves download from Hugging Face.

github.com/nvidia-cosmos/cosmos-predict2 (opens in a new tab)

git clone https://github.com/nvidia-cosmos/cosmos-predict2

Links checked 1 day ago against Hugging Face, Ollama and GitHub.

Apps that run Cosmos-Predict2 14B Video2World

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 57.6 GB 48.0 GB 29.6 GB Original weights (opens in a new tab)
FP8 38.8 GB 34.0 GB 24.7 GB Original weights (opens in a new tab)

Components

Best hardware for Cosmos-Predict2 14B Video2World

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc Pro B70 (launch price $949) at FP8.

Quality Hardware Quant Memory Speed Runs
70Great quality (A) · 70 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 RTX PRO 6000 Blackwell Workstation EditionNVIDIA RTX PRO 6000 Blackwell FP16 57.6 GB / 96.0 GB 19.5 min Slow
68Good quality (B) · 68 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 Founders EditionNVIDIA GeForce RTX 5090 FP8 24.7 GB / 32.0 GB 26.1 min SlowCPU offload
70Great quality (A) · 70 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 SXMNVIDIA H100 80GB SXM FP16 57.6 GB / 80.0 GB 18.6 min Slow
70Great quality (A) · 70 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 SXMNVIDIA H800 80GB SXM FP16 57.6 GB / 80.0 GB 18.6 min Slow
70Great quality (A) · 70 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 PCIeNVIDIA H100 80GB PCIe FP16 57.6 GB / 80.0 GB 22.7 min Slow
70Great quality (A) · 70 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 A100 80GB PCIeNVIDIA A100 80GB PCIe FP16 57.6 GB / 80.0 GB 27.8 min Slow
70Great quality (A) · 70 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 A100 80GB SXMNVIDIA A100 80GB SXM FP16 57.6 GB / 80.0 GB 27.8 min Slow
70Great quality (A) · 70 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 A800 80GBNVIDIA A800 80GB FP16 57.6 GB / 80.0 GB 27.8 min Slow
70Great quality (A) · 70 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 NVLNVIDIA H100 NVL FP16 57.6 GB / 94.0 GB 20.2 min Slow
68Good quality (B) · 68 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 L40SNVIDIA L40S FP8 38.8 GB / 48.0 GB 22.2 min Slow

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?