Scalable AI inference in a compact and ultra-low-profile design

Advantech has introduced the AIR-310, a compact edge AI inference system featuring an MXM GPU card. Powered by 12th/13th/14th Gen Intel Core 65W desktop processors, the device delivers up to 12.99 TFLOPS of scalable AI performance via the NVIDIA Quadro 2000A GPU card in a 1.5U chassis (215mm x 225mm x 55mm). Despite its compact size, it delivers versatile connectivity with three LAN ports and four USB 3.0 ports, allowing seamless integration of sensors and cameras for vision AI applications. The system includes smart fan management, operates in temperatures from 0C to 50C (32F to 122F), and is shock-resistant, capable of withstanding 3G vibration and 30G shock. Bundled with Intel Arc A370 and NVIDIA A2000 GPUs, it is certified to IEC 61000-6-2, IEC 61000-6-4, and CB/UL standards, providing stable 24/7 operation in harsh environments, including space-constrained or mobile equipment. The device supports Windows 11, Linux Ubuntu 24.04, and the Edge AI SDK, allowing accelerated inference deployment for applications such as factory inspections, real-time video surveillance, GenAI/LLM, and medical imaging.

With its high-performance computing and scalable AI capabilities, the device excels at handling multi-tasking applications. Commercial complexes boost security by combining vision and language models into surveillance systems, allowing real-time visual and textual data analysis for more accurate threat detection, improved monitoring, and proactive response. It also supports advanced imaging applications in the medical field, allowing the reconstruction and analysis of CT scans and X-rays for accurate diagnoses and preoperative assessments. Generating detailed reports on detected abnormalities and planning surgical paths improves healthcare efficiency and surgical accuracy.

The AIR-310 MXM GPU system delivers high computing power and a compact design with long-term support. By employing various GPU cards, developers can readily take advantage of software ecosystems like Intel OpenVINO, NVIDIA CUDA, and TensorRT to accelerate AI model development and deployment. It seamlessly integrates with the latest Windows 11 and Linux Ubuntu 24.04 operating systems, making it adaptable for various industries. It also supports the company's Edge AI SDK (version 3.0.0), providing a comprehensive environment for developing and running Vision AI and GenAI/LLM inference applications. This SDK eradicates compatibility issues between software and hardware and includes a no-code AI inference performance evaluation feature, significantly decreasing setup time and speeding up the development process.

The European DMS team provides a wide range of local design and manufacturing services for customers requiring customised solutions.