
MHz switching frequency-based devices enable miniaturization of the DC-DC converter and EMI filters
Achieving EMI conducted emission compliance for automobiles with a single stage filter. By Nicola Rosano, Sr. Strategic FA/System Engineer at Vicor
More details...
A full brick package developed by TDK-Lambda, the PF1500B-360, is for high voltage distributed power architectures
More details...
Combining AMD Ryzen 7000/8000/9000 Series processors, scalable GPU support (up to four PCIe slots), and Advantech’s Edge AI SDK software, these ultra-compact systems are purpose-built to meet the rising demands of data-intensive AI workloads at the edge. They can enable on-premise deployment and fine-tuning of AI models, including large language models (LLMs) and advanced AI vision inference applications, such as medical imaging and automated inspection.
Both models feature space-saving chassis, advanced thermal management, and top-grade power supplies to ensure high reliability and continuous operation. By integrating hardware and software into a single, optimised platform, the AIR-410 and AIR-420 can significantly reduce total cost of ownership, cutting expenses related to hardware, software, energy, and maintenance while also enhancing data security compared to traditional rack-mounted servers.
Compact, Quiet, and Powerful AIR-410—Supports One 3-Slot GPU for High-End Edge Inference
Powered by AMD Ryzen Embedded 8000 Series processors, the AIR-410 supports high-end GPUs, including the NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation edition, AMD Radeon PRO W7900, and Qualcomm Cloud AI 100 Ultra, delivering varying levels of AI capabilities for diverse edge AI applications. Its compact 3-slot FHFL GPU form factor and quiet operation (<38.2 dBA) make it ideal for semiconductor inspection, medical imaging, and on-premise LLM inference. Key features include an 850W power supply, support for up to 96GB DDR5 RAM and 14TB of storage, along with rich I/O interfaces. Equipped with Advantech’s Edge AI SDK, pre-validated AI models, and a no-code GUI, the AIR-410 accelerates secure and efficient AI deployment at the edge.
Scalable, Efficient, and AI-Ready AIR-420 Supports Dual High-Performance GPUs for On-Premise GenAI Post-Training
Designed for demanding AI inference and fine-tuning workloads at the edge, the AIR-420 features a compact 28.6L chassis and supports two high-performance 600W main-stream GPU cards, combining computational performance with spatial adaptability for field deployment. Paired with AMD Ryzen 7000/9000 Series processors, it delivers exceptional AI acceleration in a small footprint. With an optimised CPU/PCIe layout, redundant power design, and integrated Advantech software tools, aiSSD, aiDAPTIV , and the no-code GenAI Studio, the AIR-420 enables efficient on-premise LLM deployment and customisation. GenAI Studio is continuously updated to support the latest LLMs and provides both full-parameter and parameter-efficient fine-tuning (e.g., PEFT, LoRA), helping enterprises quickly adapt AI models for specific edge applications. This integrated solution can enable significant cost savings compared to traditional rack-mounted servers, making the AIR-420 an ideal choice for Vision AI, GenAI development, and real-time edge inference.
View PDF
| Privacy Policy | Site Map | © Copyright DFA Media
| Web design by Immersive Media

