AI inference system

Aetina MegaEdge AIP-FR68S - Scalable Edge AI Workstation for GenAI Workloads

The AIP-FR68S is specially designed for on-premises AI, LLM, and advanced AI vision inference, supporting both data center GPUs and workstation GPUs. It is compatible with NVIDIA RTX PRO 6000 Blackwell / 6000 Ada and up to three Qualcomm Cloud AI 100 Ultra accelerators (each with 870 TOPS INT8). Equipped with a modular chassis design, a 2000W power supply unit, and a PCIe Gen5 switch, the AIP-FR68S achieves scalable GPU flexibility and high-performance edge computing. By integrating the Qualcomm AI Inference Suite, it enables real-time LLM fine-tuning, multimodal analysis, and autonomous command generation, enhancing AI agents, on-premises inference, and advanced visualization. When combined with NVIDIA AI Workbench, it accelerates the development of fine-tuned generative AI models for diverse applications such as AOI-based defect detection, image enhancement in smart manufacturing, contextual knowledge management, and semantic queries for agent-based AI.

Industrial PCs