Advantech Showcases GPU Servers based on NVIDIA MGX for Scalable AI Deployment at COMPUTEX 2026

Taipei, June 2, 2026 – Taipei, Taiwan — Advantech, a leading provider of industrial edge AI and high-performance computing solutions, announces its latest GPU server portfolio designed to accelerate enterprise AI deployment—from edge to data center. By leveraging NVIDIA MGX architecture, Advantech enables flexible system design, standardized building blocks, and faster time-to-market for next-generation AI infrastructure.

The NVIDIA MGX architecture provides a modular, scalable framework that allows system providers to configure CPU, GPU, interconnect, and I/O options with greater flexibility. This approach simplifies system development while supporting a wide range of AI workloads—from edge AI inference to large-scale training in data centers—helping enterprises adapt quickly to evolving AI demands. 

To address the rapid growth of generative AI, digital twins, AI factories, and data-intensive workloads, Advantech introduces its 2U and 4U NVIDIA GPU server platforms built on the NVIDIA MGX architecture. Designed with a unified, scalable framework, both systems support up to 600W GPU configurations, including next-generation server-grade GPUs such as NVIDIA RTX PRO 6000 Blackwell Server Edition GPU, delivering exceptional compute density, thermal efficiency, and configuration flexibility for modern AI infrastructure. 

The SKY-622G4 2U GPU server is optimized for space-constrained deployments, offering a balance of performance and efficiency for AI inference, model training, and edge AI applications. Powered by dual Intel® Xeon® 6 processors and NVIDIA GPUs, it delivers strong compute performance with high-speed connectivity, enabling real-time analytics, vision AI inspection, and robotics applications where latency and reliability are critical. 

For more demanding scenarios, the SKY-642E3 4U GPU server delivers enhanced scalability and performance for large-scale AI workloads. Featuring dual AMD EPYC™ 9004/9005 processors and expanded NVIDIA GPU capacity, the platform is designed for LLM training, digital twin simulation, and multi-workload AI environments. Its optimized airflow, high-efficiency power design, and robust system architecture ensure stable operation in mission-critical deployments. These platforms support a wide range of AI-driven applications, including AI-powered smart manufacturing, autonomous robotics, industrial vision inspection, and large-scale data analytics. By enabling seamless scalability from edge to cloud, Advantech helps customers build a unified AI infrastructure to accelerate innovation and operational efficiency.

By integrating NVIDIA MGX-based modular design principles, Advantech empowers enterprises to deploy AI systems with greater flexibility, reduced integration complexity, and faster time-to-deployment—supporting the transition toward AI-driven operations and next-generation industrial intelligence. 

Advantech will showcase the latest GPU server innovations based on NVIDIA MGX at COMPUTEX 2026, highlighting how enterprises can build scalable AI infrastructure for next-generation applications—from AI factories to large-scale AI workloads. Join us at TaiNEX Hall 1, 1F, Booth #K0603a to discover how Advantech turns AI innovation into real-world impact.

Learn More

About Advantech

Advantech’s corporate vision is to enable an intelligent planet. The company is a global leader in the fields of IoT intelligent systems and embedded platforms. To embrace the trends of IoT, big data, and artificial intelligence, Advantech promotes IoT hardware and software solutions with the Edge Intelligence WISE-PaaS core to assist business partners and clients in connecting their industrial chains. Advantech is also working with business partners to co-create business ecosystems that accelerate the goal of industrial intelligence. (www.advantech.com)