Premio Rolls Out Compact Edge Server for Industrial-Grade GenAI Deployment
July 08, 2025
News
Premio Inc. released the LLM-1U-RPL, the first entry into its new LLM Series line of edge servers. The compact, short-depth (483 (W) x 480 (D) x 44 (H) mm) 1U edge server is engineered to deliver real-time Generative AI (GenAI) and Large Language Model (LLM) workloads straight to the on-premises data center moving away from general cloud dependence while offering reduced bandwidth strain, safeguarded data sovereignty, and support for real-time decisions in hybrid cloud systems at the edge.
“The LLM-1U-RPL is purpose-built for on-premise data centers to deliver high-performance, low-latency AI inferencing for large language model (LLM) workloads—without the need for traditional centralized cloud resources,” said Dustin Seetoo, VP of Product Marketing at Premio.
Key Features:
- 13th Gen Intel Core Processors (up to i9, 65W TDP)
- Supports up to an NVIDIA RTX 5000 Ada GPU for accelerated computing
- PCIe Gen 4 Expansion for GPU AI accelerators or high-throughput network cards
- Flexible and High-Speed Storage Option in m.2 NVME and dual hot-swappable 2.5” SATA bays
- Optimized I/O Connectivity for On-Premises Edge AI: 3x 2.5GbE LAN ports, 6x USB 3.2 Gen2 ports, and COM ports
- 600W (1+1) redundant power supply
- Hot-swappable redundant smart fans
- Enhanced Cybersecurity and Physical Security
- World-Class Certifications (UL, FCC, CE)
The LLM-1U-RPL supports up to 64GB of dual-channel DDR4 3200MT/s SODIMM memory for streamlining multi-modal data streams without performance holdups. It includes high-speed NVMe via an M.2 M-Key slot and front-accessible dual hot-swappable 2.5” SATA bays.
The server offers PCIe Gen 4 expansion slots for high-throughput network interface cards (NIC) or a dedicated AI GPU accelerator enabling high-performance inferencing for private, on-site LLM deployments, such as digital twins and generative AI inferencing. It is ideal for manufacturing automation and robotics, smart infrastructure, and security.
“Designed for the demands of edge deployments, this new edge server integrates 13th Gen Intel® Core™ processors with performance-hybrid architecture, dedicated NVIDIA GPUs for accelerated computing, and industrial-grade power redundancy—key capabilities that enable real-time intelligence, reduce latency, and give organizations greater control over their data,” ends Seetoo
For more information, visit premioinc.com/collections/llm-1u-rpl-series-edge-ai-rackmount-server.
Chad Cox is the Production Editor at Embedded Computing Design. His responsibilities are centered around content creation, writing and editing, and article research and development. Chad covers industry news and events and is known to interact with various industrial leaders via on-premise visits and online interviews. He is responsible for the digital footprint and dissemination of news via social media posts, advertising creation and the production of newsletters including the Embedded Computing Design’s Daily.
He is well versed in many facets of industrial computing including Edge AI, IoT, Processing, Security, Open Source, and more.
Chad graduated from the University of Cincinnati with a B.A. in Cultural and Analytical Literature and holds a master’s in education.
