Aetina Corporation, a Taiwanese edge AI solution provider and a subsidiary of Innodisk Group, today joined hands with Qualcomm Technologies, Inc. to enhance edge AI capabilities through innovative on-premises solutions.
Qualcomm introduces the Qualcomm AI On-Prem Appliance Solution and the Qualcomm AI Inference Suite for On-Prem, which leverage Qualcomm’s advanced inference accelerators alongside Aetina’s robust edge computing hardware.
Aetina MegaEdge AIP-FR68 sets a high standard in the industry by incorporating Qualcomm’s Cloud AI family of accelerator cards. Each Cloud AI 100 Ultra card can deliver a remarkable 870 TOPS of AI computing power at 8-bit integer (INT8) precision, all while consuming only 150W of power. This workstation accommodates two Cloud AI 100 Ultra cards, showcasing an exceptional balance between power and energy efficiency in a compact design.
This innovation significantly advances on-premises AI processing, making high-performance enterprise-grade computing more accessible. The Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) allow organizations to efficiently build, test, and tailor generative AI models directly on standard PC workstations, with straightforward scalability to private or cloud data environments.
Richard Hung, Vice President at Aetina, emphasized the transformative potential: “Our collaboration with Qualcomm Technologies marks a significant breakthrough in edge AI deployment. By achieving the complex landscape in a desktop form factor, we’re democratizing access to enterprise-grade AI capabilities. This solution enables businesses to run sophisticated AI models locally, ensuring data privacy while maintaining superior interoperability and cloud-level performance.”
Also Read: Aprecomm collaborates with Qualcomm to enhance Network Application IntelligenceThe Qualcomm AI On-Prem Appliance Solution synergizes processors with the comprehensive Qualcomm AI Inference Suite for On-Prem, establishing a powerful localized AI computing platform designed for optimal performance in enterprise settings.
“We are excited to introduce novel and advanced on-prem AI inference appliance solutions with Aetina,” said Rashid Attar, Senior Vice President of Engineering at Qualcomm Technologies, Inc. “These solutions address enterprise on-prem AI needs across a diverse set of sectors and, combined with the AI Inference Suite, enable a broad range of AI agents, applications, and use cases.”
This integrated solution is set to become available through global distribution partners starting in Q1 2025, keeping an effective step toward democratizing access to enterprise-grade AI capabilities for organizations of varying sizes.
