Home > AI Solutions > Gen AI > White Papers > Generative AI in the Enterprise with NVIDIA Spectrum-X Networking Platform > Compute infrastructure
Dell Technologies offers a range of acceleration-optimized servers, equipped with NVIDIA GPUs, to handle the intense compute demands of LLMs. The following server models with GPU options and networking options are available based on this design as compute resources for deploying LLM models in production:
PowerEdge R760xa servers supporting up to four NVIDIA H100 PCIe GPUs with NVLink Bridge may be used but were not validated in this version of the design.