AI is transforming how we work. Businesses save money and time and create new opportunities using state-of-the-art AI models for language, text-to-image, and code generation. With AI acceleration in every core, 5th Gen Intel Xeon processors with built-in AI accelerators like Intel® Advanced Matrix Extensions (Intel® AMX), faster memory, and larger last-level cache are ready to handle demanding AI workloads with improved performance for deep learning (DL) inference and training.

Benefit from up to 14x higher performance on PyTorch for inference and training with 5th Gen Intel Xeon processors, compared to 3rd Gen Intel Xeon processors.5 Realize up to 2.5x higher performance per watt with 5th Gen Intel Xeon processors with Intel AMX, compared to 4th Generation AMD EPYC processors.6 With nimble large-language models (LLMs) of up to 20 billion parameters, 5th Gen Intel Xeon processors meet the service-level agreements (SLAs) for delivering real-time user experiences with less than 100 ms second-token latency on LLMs.7

The HORUS220 shipboard server packs high-performance multi-core processing into an ultra-low profile rack space. With 1 PCIe add-on expansion slot and NVidia L4 and OCP3.0 NIC expansion, the 1U server can support RAID, Gen5.0 x16 graphics, or other technologies for specific workstation requirements.

Also support 8 x Gen4 x 4 M.2 swappable tray.The HORUS220 shipboard server is the ideal powerhouse workstation for optimizing rack space and performance.