NEW TAIPEI CITY, Taiwan - Aetina Corporation in New Taipei City, Taiwan, is expanding its portfolio of edge AI computing platforms to support NVIDIA Jetson T3000 and T2000 system-on-modules, enabling AI processing capabilities for robotics and industrial edge applications.

The company plans to extend its DeviceEdge AIE-KT series of fan-based edge computing systems and introduce new DeviceEdge AIE-PT fanless systems designed to support NVIDIA Jetson Thor family modules. The platforms are intended for applications requiring scalable AI inference performance in compact, power-efficient computing systems.

Aetina's DeviceEdge AIE-KT systems are designed for applications requiring additional thermal capacity and sustained computing performance, while the fanless AIE-PT systems target enclosed, rugged, and space-constrained environments requiring maintenance-free operation.

NVIDIA Jetson T3000 delivers up to 865 FP4 teraflops of AI performance through a Blackwell GPU architecture with 1,536 CUDA cores, an eight-core Arm Neoverse CPU, and 32 GB of LPDDR5X memory. The module operates within a 70-watt power envelope, according to NVIDIA specifications provided by Aetina.

The NVIDIA Jetson T2000 module provides up to 400 FP4 teraflops through a Blackwell GPU with 1,024 CUDA cores and 16 GB of LPDDR5X memory. Aetina said the module is intended for applications including visual AI, autonomous mobile robots, and robotic manipulators.

As an NVIDIA Elite Partner, Aetina has previously developed edge AI systems based on NVIDIA Jetson AGX Thor modules. The company said its expanded Jetson Thor portfolio will support NVIDIA's software ecosystem, including AI models and development tools for physical AI and robotics applications.

Aetina expects NVIDIA Jetson T3000 and T2000-based systems to become available in the first quarter of 2027.

For more information, please visit https://www.aetina.com.