NVIDIA Launches Cosmos 3 Edge: 4B-Parameter World Model for Robotics
NVIDIAAI · x · 2026-07-28
NVIDIA has released the Cosmos 3 Edge model on Hugging Face. It is a 4-billion-parameter compact open world model designed specifically for robots and vision AI agents on edge devices.
The model delivers memory-efficient, high-throughput inference across NVIDIA's edge computing lineup, including Jetson modules and RTX GPUs. Functioning as a World Action Model (WAM), it achieves real-time control at 15Hz on Jetson Thor, generating 32 actions per inference. Among models of similar size, Cosmos 3 Edge ranks #1 in vision analytics and sets the state-of-the-art for robot policy learning.
Related event: NVIDIA Unveils Cosmos 3 World Foundation Models(2 posts)→
More from Embodied
- iPhone Duo preorders sell out in 3 minutes around NYC, deliveries slip to late November — BenBajarin · 2026-10-16
- UMD's PAIR framework bridges perception and action in VLA models via bridge tokens — Kaixi Feng · 2026-10-16
- CI-MSE offline metric hits -0.87 Spearman correlation with real robot task success vs weak raw MSE — chris_j_paxton · 2026-10-16
- List of 15 best robotics researchers on X, from Jim Fan to Chelsea Finn and Fei-Fei Li — FinanceYF5 · 2026-10-16
- Fake Apple listing for dual-screen 'iPhone Duo' jokes it's the best phone for watching your AI agents — AIFlow_ML · 2026-10-16
- Inside Auki's Hong Kong office: a fake grocery store powering robotics data collection — LoganGrasby · 2026-10-16