HPE ProLiant DL385 Gen11 Rack Server (AMD EPYC)

The HPE ProLiant DL385 Gen11 is a 2U rack-mount server built on the AMD EPYC 9004 series (Genoa) processor architecture, delivering exceptional core density and memory bandwidth for enterprise consolidation workloads. Supporting up to two 4th Gen AMD EPYC processors with up to 96 cores each (192 total cores per system), the platform pairs with up to 6TB of DDR5 memory across 24 DIMM slots, enabling high virtual machine density and in-memory data processing at scale. The server leverages PCIe 5.0 fabric for high-throughput I/O connectivity to accelerators, NVMe storage, and networking adapters.

Designed around HPE's Compute Scale-Up architecture, the DL385 Gen11 supports flexible storage configurations including front-accessible NVMe, SAS, and SATA drive bays, with options for up to 24 SFF or 12 LFF drives depending on configuration. Integrated HPE iLO 6 management delivers remote server lifecycle management, firmware compliance, and security monitoring, while HPE's Silicon Root of Trust technology anchors firmware integrity from the hardware level upward. The platform is optimized for software-defined infrastructure and cloud-native deployments through compatibility with VMware vSphere, Red Hat OpenShift, and Microsoft Azure Stack HCI.

The DL385 Gen11 targets enterprises seeking to maximize compute-per-rack-unit efficiency while reducing infrastructure footprint. Its combination of high core count, large memory capacity, PCIe 5.0 expansion, and a broad ecosystem of HPE and third-party accelerators makes it well suited for virtualization consolidation, VDI, HPC, AI inference, and data-intensive analytics. The platform ships with HPE's embedded security posture and integrates natively into HPE GreenLake cloud services for hybrid IT management.

Ideal for

• Large-scale server virtualization consolidation using VMware vSphere or Red Hat OpenShift, leveraging high core counts to maximize VM density per 2U chassis
• Virtual Desktop Infrastructure (VDI) deployments requiring high concurrent user sessions with consistent per-session CPU and memory resource allocation
• In-memory database and real-time analytics workloads such as SAP HANA or Redis, benefiting from up to 6TB DDR5 memory and high memory bandwidth
• AI inference and machine learning workloads using PCIe 5.0-attached GPU accelerators for high-throughput model serving in enterprise data centers
• High-performance computing (HPC) clusters and simulation workloads that benefit from the high aggregate core count and NUMA-optimized AMD EPYC architecture
• Hybrid cloud edge node deployments integrated with HPE GreenLake, providing on-premises compute with cloud-consistent management and observability

Technical specifications

Available from Omnixon Global. Submit an RFQ and our team will confirm configuration and availability for your order.