Nvidia · Hugging Face
Cosmos 3 is an open world foundation model service
Compiled by KHAO Editorial — aggregated from 1 source + 1 reference discovered via search. See llms.txt for citation guidance.
★ Tier-1 Source
As models are post-trained with high-quality, domain-specific data, their accuracy continue to improve for specialized applications.
Key facts
- As a post-trained world action model (WAM), Cosmos 3 Edge operates at robot-control resolution (640×360 observations), delivering real-time reasoning and generating 32 actions per inference on NVIDIA
- Cosmos 3 Super 4-Step (Text-to-Image & Image-to-Video): These are distribution-matching distilled checkpoint and scripts that reduce diffusion from 35–50 denoising steps to 4, delivering up to 25×
- The team are also releasing Cosmos 3 Edge Policy (DROID): A robot manipulation policy post-trained on the DROID dataset for pick-and-place tasks, with accompanying post-training scripts
- To demonstrate this workflow, they're also releasing the Cosmos 3 Super 4-Step Distillation checkpoint along with a post-training script, providing a faster reference implementation for 64B model
Summary
The model delivers memory-efficient, high-throughput inference across NVIDIA edge computers including NVIDIA RTX PRO GPUs, NVIDIA DGX, NVIDIA GeForce RTX™ GPUs, NVIDIA Jetson including the newly announced Jetson T2000 and T3000 modules. Designed as a compact open model that can serve as a small vision language model (VLM) with best-in-class throughput and accuracy with real-time inference. As a post-trained world action model (WAM), Cosmos 3 Edge operates at robot-control resolution (640×360 observations), delivering real-time reasoning and generating 32 actions per inference on NVIDIA Jetson Thor - while achieving real-time control at 15 Hz. Among similar size (4B parameters) models, Cosmos 3 Edge ranks #1 on VANTAGE-Bench for vision analytics and state-of-the-art for robot policy learning, setting the state of the art for smart infrastructure and robotics. Consider a robot reaching for an object.