ASUS IoT has announced the PE3000N, a compact edge Artificial Intelligence platform built around the NVIDIA Jetson Thor architecture and a Jetson T5000 module. The system combines an advanced NVIDIA Blackwell GPU with a 14-core Arm CPU and up to 128 GB of LPDDR5X memory, delivering up to 2,070 FP4 TFLOPS of Artificial Intelligence processing power. ASUS positions the PE3000N for tight integration into robotic systems and other deployments where space and energy efficiency are critical, enabling on-device model execution and high-throughput inference.
The PE3000N emphasizes rugged reliability for demanding environments. The chassis uses MIL-STD-810H industrial-grade connectors and a low-profile form factor to withstand harsh operating conditions. For sensor and camera integration it supports up to 16 GMSL cameras and offers up to four optional 25GbE links, enabling high-bandwidth sensor fusion and advanced machine vision. Power management is designed for diverse field use with a wide 12 to 60 V DC input and ignition support, and the unit is rated to operate from minus 20 degrees Celsius up to 60 degrees Celsius to maintain stable, battery-friendly operation across mobile and industrial scenarios.
ASUS frames the PE3000N as a platform for developers and system integrators to advance autonomy, sensor fusion and Artificial Intelligence-driven control in industrial, commercial and smart infrastructure settings. The combination of dense compute, broad I/O and ruggedized design targets mission-critical robotics, automation and edge deployments where performance, secure data handling and resilience are required. The announcement highlights the PE3000N’s role in enabling high-bandwidth perception and control workflows at the edge using NVIDIA’s latest Jetson family silicon.
