2026-06-03 ASRock Industrial and Phison Redefine Edge AI Deployment with Advanced Memory Expansion
Taipei, Taiwan (June 3, 2026) – ASRock Industrial and Phison Electronics today announced a strategic collaboration to accelerate large-scale local AI deployment through next-generation AI memory expansion powered by Phison aiDAPTIV™ technology. Together, ASRock Industrial AI BOX-A395 and Phison aiDAPTIV™ enable 120B-parameter large language models to run locally with only 64GB of system memory and 85GB of aiDAPTIV™ cache memory, reducing traditional memory requirements by up to 50% and significantly lowering the barrier for large-scale edge AI deployment. At Computex 2026, both companies further demonstrated this solution, enabling large-scale LLMs to run stably on-device and delivering a highly efficient and seamless edge AI experience. This collaboration delivers next-generation edge AI with reduced total cost of ownership (TCO), faster inference performance, and support for larger AI workloads on compact edge devices. This breakthrough enables scalable local LLM deployment across ASRock Industrial’s latest Edge AI platforms, providing greater flexibility for enterprise and industrial AI applications. ASRock Industrial will also feature validated Phison aiDAPTIV™ configurations through its AI-Pathfinder tool, helping customers identify optimized AI systems based on workload requirements and deployment scenarios.
Unlocks More Efficient Local LLM Deployment
ASRock Industrial’s latest Edge AI platforms, powered by Phison aiDAPTIV™, enable more efficient and scalable local AI LLM deployment across diverse edge environments. The AI BOX-A395 with AMD Ryzen™ AI Max+ 395 reduces system requirements for large-scale AI workloads, while the NUC Ultra 300 BOX Series with Intel® Core™ Ultra Series 3 CPU enables on-device inference of large language models in a compact form factor. Leveraging aiDAPTIV™’s MoE (Mixture of Experts) inference architecture, AI BOX-A395 can run 120B-parameter LLMs with only 64GB system memory, while 128GB configurations intelligently offload model data to SSD cache, freeing DRAM/VRAM for operating systems, edge agents, and additional AI workloads. This architecture improves overall system utilization and enables a single edge device to handle inference and multi-task AI workloads simultaneously. By transforming SSD into a high-speed memory layer optimized for AI inference, aiDAPTIV™ removes traditional memory constraints and enables larger models to run more efficiently without relying on oversized infrastructure, significantly enhancing flexibility and deployment scalability for real-world edge AI applications.
“AI is rapidly moving beyond centralized infrastructure and into real-world environments where intelligence must operate closer to where data is created,” said James Lee, Chairman of ASRock Industrial. “Together with Phison, we are advancing a new approach to local AI deployment, breaking through the memory configuration limitations of traditional systems and enabling larger AI models to be deployed where real value is created. We believe scalable local AI will become a defining foundation for the next generation of enterprise and industrial computing. Future AI infrastructure competition will depend not only on compute power, but also on memory efficiency.”
As AI workloads continue shifting toward local and on-premise deployment, ASRock Industrial and Phison are advancing a new generation of scalable AI infrastructure designed to bring larger models, greater efficiency, and more flexible deployment closer to where intelligence is needed most. By combining high-performance edge AI platforms with next-generation memory expansion architecture, the collaboration represents a significant step toward making large-scale local AI more accessible, practical, and ready for real-world deployment across enterprise and industrial environments. To simplify AI adoption and accelerate deployment decisions, ASRock Industrial continues expanding its AI-Pathfinder tool with validated AI platform recommendations, including accelerator cards, GPUs, and optimized hardware configurations tailored for different AI workloads and deployment scenarios. Through AI-Pathfinder, customers can more easily identify recommended systems and accelerate their path toward scalable edge AI deployment.
To explore recommended AI platform configurations through the AI-Pathfinder tool, please visit our website or use the AI-Pathfinder tool.
About Phison Electronics
Phison Electronics Corp. (TPEX:8299) is a global leading provider of NAND flash controller ICs and storage solutions. As the industry evolves, Phison has transformed from a traditional controller IC design company into an integrated platform service provider combining AI computing and storage technologies, focusing on high-value and customized markets. Leveraging its expertise in firmware algorithms, controller IC design, and system integration, Phison provides one-stop services ranging from IP licensing and chip design to system architecture and turnkey solutions. Its technologies are widely adopted across data centers, AI computing, enterprise storage, industrial PCs, and embedded systems. Through close collaboration with global NAND manufacturers and ecosystem partners, Phison helps customers accelerate design-in processes and deliver high-performance, reliable, and differentiated storage and AI solutions.