System Description
The Mayflower®-LLM18-SP3 is a 19″ GenAI server specifically designed for AI inference and model fine-tuning. The server is equipped with an AMD® EPYC™ CPU and supports up to three NVIDIA® RTX 6000 Ada GPUs, each with 48 GB of GDDR6 and 18176 CUDA Cores. The server offers impressive AI performance with up to 1457 TFLOPs.
For expansions, there are seven PCIe x16 slots available. In terms of network connectivity, the server provides two 10 GBit LAN ports and two 100 GBit LAN ports with NVIDIA® ConnectX®-6 Dx technology. The server is designed for 24/7 operation and uses robust, industrial-grade components. Supported operating systems are Microsoft® Windows® Server and Linux®.
Find out more
about Generative AI.
