Dell PowerEdge R860 Specs and Features
Four Sockets. Two Rack Units. Engineered for Business-Critical Density
Form Factor — 2U rack server, 16th Generation PowerEdge (Gen 16); air-cooled design optimized for high server density
Four-Socket Architecture — Supports up to four 4th Gen Intel® Xeon® Scalable processors (Sapphire Rapids); unique PEM board stacks CPUs 3 and 4 on top of CPUs 1 and 2 within the slim 2U chassis
Maximum Core Count — Up to 60 cores per socket; 240 total cores across all four sockets for the most demanding parallel workloads
Memory Capacity — 64 DDR5 RDIMM slots delivering up to 16 TB of memory at speeds up to 4800 MT/s — ideal for large in-memory database deployments
PCIe Gen 5 Expansion — 8 PCIe Gen 5 expansion slots across 4 riser configurations on 6 risers — double the per-lane bandwidth of PCIe Gen 4
Flexible Storage — Drive configurations from 8 to 24 × 2.5-inch SFF bays, plus 8 × EDSFF E3.S Gen5 NVMe option; supports SAS4, SATA, and NVMe simultaneously
Dimensions — 482 mm W × 86.8 mm H × 883.2 mm D (with bezel); fully loaded weight: 42.97 kg (94.73 lbs)
Optional Intel QuickAssist — On-chip acceleration for cryptography, data compression, and storage analytics; no discrete accelerator card required
Engineered for Demanding Business-Critical Applications
In-Memory Databases — 16 TB of DDR5 memory enables SAP HANA, Oracle In-Memory, and Microsoft SQL Server in-memory configurations that previously required larger chassis footprints
Business-Critical Virtualization — 240 cores across 4 sockets run massively parallel VM workloads; high vCPU-to-core ratios and near-native performance for VMware vSphere and KVM deployments
ERP & Line-of-Business Applications — Four-socket performance handles peak transaction loads for SAP ERP, Oracle EBS, and Microsoft Dynamics without vertical scaling constraints
HPC & Technical Computing — PCIe Gen 5 fabric and 240 compute cores accelerate simulation, modeling, and parallel computational workloads at reduced per-socket cost
AI / ML Training Inference — Sapphire Rapids built-in AMX (Advanced Matrix Extensions) accelerates AI matrix math operations directly on-chip without dedicated GPU cards for many inference workloads
Consolidation Workloads — Replace multiple two-socket servers with a single R860; consolidate compute density while protecting capital investment in existing rack infrastructure
Data Analytics & OLAP — Massive memory bandwidth from DDR5 across four sockets feeds high-speed analytics engines processing terabytes of in-memory data sets
4th Gen Intel® Xeon® Scalable — Up to 240 Cores Across Four Sockets
Socket — LGA4677; supports up to four 4th Gen Intel® Xeon® Scalable (Sapphire Rapids) processors; minimum one CPU required (CPUs 3 and 4 require PEM board installation)
Maximum Core Count — Up to 60 cores per socket; 240 total cores when all four sockets are populated — unmatched parallelism in a 2U chassis
Intel UPI Interconnect — Up to four Intel Ultra Path Interconnect (UPI) links at up to 16 GT/s per link for high-bandwidth, low-latency multi-socket communication
PCIe Gen 5 I/O — Up to 80 PCIe Gen 5 lanes per socket at 32 GT/s per lane; 2× the bandwidth of PCIe Gen 4 for NVMe storage and high-throughput network adapters
Built-In Accelerators — Intel QuickAssist Technology (QAT) for cryptography and compression; Intel AMX for AI matrix math; hardware accelerators for networking and storage — all on-die, no expansion card needed
Heatsink Guide — Standard (STD) ≤ 185 W; L-type High Performance (HPR) 195–250 W; L-type Very High Performance (VHPR) ≥ 270 W — each CPU needs its own heatsink
Processor Mixing — Mixing different processor models in a 4-socket configuration is not recommended; all four sockets should be populated with identical CPUs
Optional Intel QuickAssist — Available on supported Sapphire Rapids SKUs; offloads cryptography (AES-GCM, SHA) and LZS/Deflate compression from application cores to dedicated accelerator engines
64 DDR5 DIMM Slots — Up to 16 TB at 4800 MT/s
DIMM Slots — 64 total slots (16 per processor); 32 slots on the main board (CPUs 1–2) and 32 additional slots on the PEM board (CPUs 3–4); all four processors required for full 64-DIMM population
Maximum Capacity — 16 TB total when all 64 slots are populated with the highest-density DDR5 RDIMMs — the largest in-chassis memory capacity in the Gen 16 rack server lineup
Operating Speeds — 4800 MT/s at 1 DIMM per channel (1DPC); 4400 MT/s at 2 DIMMs per channel (2DPC); DDR5 delivers ~50% more bandwidth per pin vs DDR4
Memory Type — Registered ECC DDR5 RDIMMs only; DDR4 is NOT supported on the R860; this server requires DDR5 in all configurations
Voltage — 1.1 V DDR5 operation; improved power efficiency per gigabyte compared to DDR4's 1.2 V baseline
PEM Board Memory — The Power Enable Module (PEM) board adds 32 DIMM slots when CPUs 3 and 4 are installed; without the PEM board (2-socket config) the server is limited to 32 DIMM slots and 8 TB maximum
ECC Protection — All DIMMs provide Error Correcting Code protection; essential for business-critical in-memory databases where a single bit error cannot be tolerated
Flexible SFF Bay Configurations — 8 to 24 Hot-Swap Drives
8 × 2.5" SFF — Entry configuration; supports SAS/SATA drives; ideal for boot + fast application storage while PCIe slots remain free for network or accelerator cards
16 × 2.5" SFF (SAS4/SATA) — Mid-range SFF configuration supporting 24 Gb/s SAS4 and SATA drives for high-throughput block storage
16 × 2.5" SFF + 8 × 2.5" NVMe — Hybrid configuration combining SAS4/SATA capacity drives with 8 NVMe SSDs for high-performance tiered storage
24 × 2.5" SFF (SAS4/SATA) — Maximum SFF bay count; supports all SAS4/SATA; optional add-on of 2 additional 2.5-inch NVMe or SAS/SATA drives in dedicated slots
24 × 2.5" NVMe Passive — All-flash NVMe configuration with 24 passive NVMe bays over PCIe Gen 5; the highest-performance storage option for latency-sensitive workloads
16 × 2.5" NVMe RAID — NVMe RAID configuration using APERC; delivers hardware RAID protection across NVMe drives without sacrificing NVMe performance
Dual Controller Options — 24-bay SAS4/SATA configurations are available with Dual PERC controllers for redundant RAID paths — critical for high-availability storage deployments
Hot-Swap Support — All drive bays support hot-swap replacement; failed drives can be swapped without powering down the server, minimizing downtime for business-critical applications
8 × EDSFF E3.S Gen5 NVMe — Next-Generation Flash Storage
EDSFF E3.S Form Factor — Enterprise and Datacenter Standard SSD Form Factor (E3.S); designed to overcome the areal density and thermal limitations of 2.5-inch U.2 drives
PCIe Gen 5 NVMe — Each EDSFF E3.S drive connects over PCIe Gen 5, delivering up to 2× the sequential bandwidth per drive vs PCIe Gen 4 NVMe
8-Drive Configuration — Up to 8 × EDSFF E3.S (NVMe) Gen5 drives; purpose-built for the highest-density, lowest-latency flash workloads in a 2U footprint
Higher Density Per Bay — EDSFF longer form factor allows higher-capacity NAND configurations per drive than equivalent U.2 2.5-inch enclosures
Ideal for AI/ML & HPC — PCIe Gen 5 NVMe delivers the storage bandwidth required to feed 240-core compute configurations without I/O bottlenecks
Improved Thermal Management — E3.S form factor improves airflow around NAND packages versus traditional 2.5-inch drives, enabling higher sustained write performance in dense 2U environments
Separate from SFF Bays — The EDSFF configuration is a distinct chassis option; not combined with the standard 24 × 2.5-inch SFF layout — choose based on workload requirements
PERC 11 & PERC 12 RAID — fPERC, Dual PERC, and APERC Options
PERC 12 (H965i & H965e) — Latest-generation RAID controller; 24 Gb/s SAS4 + PCIe Gen 5 NVMe; supports RAID 0/1/5/6/10/50/60; 8 GB NV-backed cache; highest throughput for SAS4 drive deployments
PERC 11 (H755 & H355) — 12 Gb/s SAS RAID controllers; support RAID 0/1/5/6/10/50/60; H755 includes 8 GB NV cache; H355 is entry-level without cache but with broader drive support via SAS expander
fPERC (Front PERC) — Front-mounted PERC controller saves one PCIe slot for other expansion cards; ideal for configurations requiring RAID control without consuming riser slot resources
Dual PERC Configuration — Available on 24-bay SFF deployments; provides two independent RAID controllers for redundant storage paths — critical for high-availability environments where a single controller failure cannot interrupt I/O
APERC (Advanced PERC) — An APERC takes up one PCIe riser slot; used in configurations where additional PERC flexibility is required beyond what fPERC or the standard PERC slot provides
HBA Pass-Through — HBA (non-RAID) mode available for software-defined storage, SDS, or OS-based RAID configurations where the application manages RAID directly
BOSS Boot Module — Boot Optimized Storage Subsystem (BOSS) provides dedicated NVMe M.2 RAID-1 boot mirror; keeps OS drives separate from data drives; does not consume a drive bay or PCIe riser slot
8 PCIe Gen 5 Slots — 4 Riser Configurations on 6 Risers
PCIe Gen 5 Throughout — All 8 expansion slots operate at PCIe Gen 5 (32 GT/s per lane); 2× lane bandwidth vs PCIe Gen 4 for NVMe adapters, InfiniBand, and 400GbE networking cards
6 Riser Cards, 4 Configurations — Risers R1b, R1c, R2, R3, R4b, and R4c; choose the riser combination that matches your slot count, slot width, and half-height/full-height requirements
Slot Width Matching — Review slot width (x8 vs x16) before installing expansion cards; placing a x16-interface card into a x8 physical slot will result in reduced performance
System Board Slots — Additional expansion card slots are supported directly on the system board without consuming riser positions; consult technical guide for system board slot positions and lengths
APERC Consideration — Adding an Advanced PERC (APERC) controller consumes one PCIe slot; factor this in when planning riser configuration and remaining slot availability for network or accelerator cards
OCP Slot (Separate) — The OCP 3.0 network slot is isolated from the 8 PCIe riser slots; adding an OCP card does not reduce your available PCIe expansion slots
fPERC Slot Savings — Using a front-mounted fPERC controller instead of a standard PERC card preserves all 8 PCIe slots for network and accelerator expansion
2 × LOM Built-In + Optional OCP 3.0 Up to 100 GbE
Built-In LOM Ports — Two LOM (LAN on Motherboard) ports included by default in every R860 configuration; provides baseline network connectivity without consuming a PCIe riser slot
OCP 3.0 Slot — Dedicated OCP (Open Compute Project) 3.0 network slot supports optional OCP network adapter cards with up to 100 GbE total bandwidth across 4 ports (25 GbE × 4)
PCIe Slot Independence — The OCP slot is separate from the 8 PCIe riser slots; installing an OCP card does not consume or reduce available PCIe expansion slots — the recommended method for expanding network bandwidth
25 GbE / 100 GbE Options — OCP cards available with 4 × 25 GbE ports (100 GbE aggregate) for high-throughput database replication, storage area network traffic, and east-west virtualization networking
10 GbE OCP Options — Entry OCP adapters with 4 × 10 GbE provide cost-effective high-speed networking for environments not yet requiring 25/100 GbE bandwidth
InfiniBand via PCIe — HDR/NDR InfiniBand adapters can be installed in PCIe Gen 5 riser slots for MPI-based HPC cluster connectivity and lossless fabric requirements
iDRAC Dedicated Port — A separate 1 GbE iDRAC9 dedicated management port is available for out-of-band server management completely isolated from production network traffic
Redundant Hot-Swap Power Supplies
Dual PSU Required for Redundancy — Two PSUs must be installed for 1+1 redundant operation; if one PSU fails, the server continues running on the surviving unit, though system performance may be reduced until the failed PSU is replaced
Hot-Swap Capable — PSUs can be replaced without powering down the server in dual-PSU configurations; swap the failed unit while the system remains live — critical for 24/7 business-critical deployments
High-Wattage Options — The four-socket R860 supports high-wattage PSUs appropriate for a fully loaded 4-socket, 24-drive, 8-PCIe-slot configuration; consult the technical guide for PSU wattage vs CPU TDP
Platinum / Titanium Efficiency — Available in 80 PLUS Platinum and Titanium efficiency ratings; Titanium-rated PSUs minimize energy waste at typical server load levels, reducing electricity costs over the platform lifetime
Performance Reduction on Single PSU — Operating with a single PSU (after a failure) may trigger frequency caps or thermal throttling to stay within the surviving PSU's power budget — replace failed PSUs promptly
Power Budget Planning — A fully populated R860 (four 60-core CPUs + 64 DIMMs + 24 SFF drives + 8 PCIe cards) draws substantially more power than a 2-socket configuration; right-size PSU wattage at order time
High-Density Air Cooling — Optimized for Four-Socket 2U Efficiency
Air-Cooled Architecture — The R860 is an air-cooled design; Dell engineering optimized the chassis airflow to efficiently cool four CPUs, 64 DIMMs, and up to 24 drives within the slim 2U form factor — no liquid cooling infrastructure required
Fan Cage Assembly — Modular fan cage provides high-volume airflow across the main board, PEM board, and all drive bays; fans are hot-swap replaceable in most configurations
Heatsink Selection by CPU TDP — Standard (STD) heatsink for CPUs ≤ 185 W; L-type High Performance (HPR) for 195–250 W CPUs; L-type Very High Performance (VHPR) for CPUs ≥ 270 W; each socket requires its own heatsink
PEM Board Cooling — The Power Enable Module (PEM) board carries CPUs 3 and 4 along with their heatsinks; the chassis fan subsystem is designed to direct airflow across both the PEM board and the main board simultaneously
Drive Bay Airflow — All empty drive bays must have blanks installed to maintain proper pressure differentials and prevent hot-air recirculation across drive backplanes
ASHRAE A2 Compliance — Server is designed to operate within ASHRAE A2 datacenter environments (ambient up to 35°C) at standard CPU TDP levels; verify thermal limits for high-TDP CPU configurations
Isobaric Pressure Management — Dell's fan speed management algorithms continuously adjust fan RPM based on real-time thermal sensor data from CPUs, DIMMs, drives, and PCIe cards to balance acoustics and cooling efficiency
Rear Ports — iDRAC Direct, USB, VGA, and Networking
Rear USB Ports — Two USB 3.0 Type-A ports on the rear panel for external storage device connections, bootable USB drives, and management tools
Front USB Port — One USB 3.0 Type-A port on the front panel for local access without requiring rear connection
VGA Port — One DB-15 VGA port on the rear panel provides direct console video output for local keyboard-monitor-mouse (KMM) connections
iDRAC Direct (micro USB) — Micro-USB port on the rear panel provides iDRAC direct laptop interface for out-of-band management access without requiring a dedicated network connection
Dedicated iDRAC NIC — Separate 1 GbE RJ45 iDRAC9 dedicated management port; keeps management traffic on an isolated network segment from production data traffic
LOM Data Ports — Two built-in LOM RJ45 or SFP+ ports for production network traffic; supplement with OCP 3.0 card for additional 10/25/100 GbE ports
SD Card Slot — Internal MicroSD card slot available for hypervisor boot or OS media; keeps boot media off primary drive bays
PCIe Slot Rear Access — Eight PCIe Gen 5 riser slots exit through the rear panel; full-height and low-profile bracket options available depending on riser card configuration
Cyber Resilient Architecture — Root of Trust at the Silicon Level
Silicon Root of Trust — Cryptographic identity baked into the server's silicon at manufacturing; the server can only boot firmware that has been cryptographically signed and verified — supply chain attack mitigation at the hardware level
Secured Component Verification (SCV) — Digitally verifies that server components are authentic Dell-sourced parts; SCV certificates are checked at power-on to detect unauthorized component substitution during shipping or staging
System Lockdown Mode — iDRAC9 System Lockdown prevents firmware, configuration, and BIOS changes without explicit administrator authorization; ideal for PCI-DSS, HIPAA, and FedRAMP compliance environments
BIOS Signed Firmware — All BIOS firmware updates are cryptographically signed by Dell; downgrade attack prevention ensures the server cannot be forced to run a vulnerable older BIOS version
TPM 2.0 — Trusted Platform Module 2.0 provides hardware-based key storage and measured boot capability for BitLocker, vTPM, and zero-trust platform attestation workflows
Secure Boot — UEFI Secure Boot verifies OS bootloader signatures before handing over control; prevents unauthorized or malware-infected operating systems from loading during boot
iDRAC Enterprise License Security Features — Certificate-based authentication, two-factor authentication support, RSA SecurID integration, LDAP/Active Directory authentication, and role-based access control for granular privilege management
Drive Data Protection — Self-Encrypting Drive (SED) support for instant cryptographic drive wiping at end-of-life; drive data is unrecoverable without the encryption key — eliminates sanitization costs
iDRAC9 Management — Full Lifecycle Control from Any Location
iDRAC9 (Integrated Dell Remote Access Controller 9) — Out-of-band management controller operates independently of the server OS; manage, monitor, and remediate the R860 even when the OS is unresponsive or powered off
iDRAC9 License Tiers — Express (base), Enterprise, and Datacenter licenses; Datacenter license unlocks OpenManage Integration with VMware vCenter, multi-server dashboard, and advanced telemetry streaming
Redfish API — Full DMTF Redfish 1.x RESTful API support; enables infrastructure-as-code management via Ansible, Terraform, and PowerShell DSC without installing in-OS agents
OpenManage Enterprise — Dell's centralized management console monitors and configures multiple PowerEdge servers from a single interface; supports firmware update orchestration, configuration compliance, and alert management
Virtual Console & Virtual Media — Remote KVM console access with virtual CD/DVD and USB media mounting; deploy or re-image the OS remotely without physical datacenter access
iDRAC Direct (Laptop Interface) — Micro-USB port allows a direct laptop-to-iDRAC connection via RNDIS for local management without a network switch — ideal for initial provisioning or emergency access
Automated Firmware Updates — iDRAC9 can trigger Dell Repository Manager-driven multi-component firmware updates across the entire server (BIOS, PERC, NICs, PSUs) in a single orchestrated operation
Telemetry Streaming — Real-time CPU, memory, PCIe, and power telemetry streamed via Redfish SSE or Kafka to monitoring platforms such as Splunk, Grafana, and custom SIEM solutions
Power Enable Module — How the R860 Fits Four Sockets in 2U
What Is the PEM Board? — The Power Enable Module (PEM) is a secondary planar board installed on top of the first two processors; it physically holds CPUs 3 and 4 plus their 32 DDR5 DIMM slots — enabling true 4-socket compute in a 2U chassis
Vertical Stacking Design — By mounting the PEM board over CPUs 1 and 2, Dell eliminates the need for a wider chassis or a 4U form factor; this vertical stacking approach is what differentiates the R860 from conventional 4-socket solutions
Required for 3rd and 4th CPU — The PEM board must be installed before CPUs 3 and 4 can be seated; a 2-socket R860 without the PEM board operates normally with 32 DIMM slots and 8 TB max memory
32 Additional DIMM Slots — The PEM board adds 32 DDR5 RDIMM slots (16 per CPU 3/4 socket), bringing the total to 64 slots and enabling the full 16 TB memory configuration
Airflow Integration — The chassis fan subsystem is engineered to deliver sufficient airflow across both the main board and the elevated PEM board simultaneously; thermal design accounts for the stacked CPU arrangement
Install Sequence — CPUs 1 and 2 are installed first on the main system board; the PEM board is then seated on top; CPUs 3 and 4 are installed last into the PEM board sockets
Business Benefit — Organizations that need 4-socket scalability without dedicating 4U of rack space gain a significant density advantage; the R860 delivers the compute of a 4U 4-socket server in half the rack footprint
ReadyRails II Sliding Rails — Tool-Less 4-Post Rack Mounting
ReadyRails II — Dell's ReadyRails II sliding rail kit supports tool-less installation in 4-post EIA-310-compliant racks with square, round, or threaded holes; no rack-specific hardware adapters required for most standard rack enclosures
Full Extension — Sliding rails extend fully to allow complete server removal from the rack without disconnecting cables; simplifies drive installation, PCIe card replacement, and memory upgrades in deployed racks
CMA (Cable Management Arm) — Optional Cable Management Arm attaches to the rail kit and routes power and data cables neatly along the server chassis; cables flex with the sliding rails so the server can be extended without cable disconnection
2U Standard Depth — 883.2 mm with bezel (34.77 inches); 869.2 mm without bezel (34.22 inches); compatible with most standard 1000 mm and 1100 mm deep rack enclosures
Weight Capacity — Fully loaded weight of 42.97 kg (94.73 lbs); verify rail kit and rack enclosure weight ratings before installing a fully populated 4-socket, 64-DIMM, 24-drive R860
2U Footprint Efficiency — At 2U high, the R860 provides 4-socket compute density that previously required 4U in legacy Dell, HP, and IBM 4-socket platforms; every 2U saved allows one more server in a standard 42U rack
R860 Gen 16 vs R840 Gen 14 — The Case for Upgrading
PCIe Generation Leap — R860 delivers PCIe Gen 5 (32 GT/s per lane) vs PCIe Gen 3 (8 GT/s per lane) on the R840; 4× the per-lane bandwidth for NVMe storage and 100 GbE networking
Memory Bandwidth — DDR5 at 4800 MT/s vs DDR4 at 3200 MT/s; ~50% improvement in memory bandwidth feeds data to Sapphire Rapids' enhanced core cache hierarchy faster than any DDR4 platform could
Maximum Memory — R860 supports up to 16 TB (64 × DDR5 RDIMMs) vs R840's 6 TB maximum (48 × DDR4 LRDIMMs); nearly 3× more in-memory capacity for SAP HANA and Oracle scale-up deployments
Core Count Growth — Up to 240 cores (4 × 60c Sapphire Rapids) vs up to 224 cores (4 × 56c Cooper Lake / Cascade Lake); more cores plus Intel AMX built-in AI acceleration
RAID Controller Generation — PERC 12 (24 Gb SAS4 + PCIe Gen 5 NVMe) vs PERC 10 (12 Gb SAS + PCIe Gen 3); 2× SAS bus bandwidth for all-flash SAS4 arrays
Security Enhancements — R860 adds Secured Component Verification (SCV) supply-chain attestation and Silicon Root of Trust improvements; R840 had early Cyber Resilient Architecture without SCV
Form Factor Unchanged — Both platforms are 2U; upgrading from R840 to R860 requires no rack reconfiguration — swap the server in the same 2U slot
| Feature | R860 (Gen 16) | R840 (Gen 14) |
|---|---|---|
| CPU Generation | 4th Gen Xeon Scalable (Sapphire Rapids) | 2nd Gen Xeon Scalable (Cascade Lake) |
| Max Cores | 240 (4 × 60 cores) | 224 (4 × 56 cores) |
| PCIe Generation | PCIe Gen 5 (32 GT/s) | PCIe Gen 3 (8 GT/s) |
| Memory Type | DDR5 at 4800 MT/s | DDR4 at 3200 MT/s |
| Max Memory | 16 TB (64 DIMM slots) | 6 TB (48 DIMM slots) |
| PERC Controller | PERC 12 (24 Gb SAS4) | PERC 10 (12 Gb SAS) |
| On-Die Accelerators | QAT, AMX, IAA, DSA (Sapphire Rapids) | None (software-only) |
| Security | Silicon Root of Trust + SCV | Cyber Resilient Architecture (no SCV) |
| Management | iDRAC9 Rev. 7+ with Redfish 2.x | iDRAC9 Rev. 4.x |
| Form Factor | 2U (883.2 mm depth) | 2U (876.8 mm depth) |
Frequently Asked Questions — Dell PowerEdge R860
The Dell PowerEdge R860 supports up to 16 TB of DDR5 ECC memory across a quad-socket platform — the industry’s highest density for rack-based database consolidation, essential for Tier-1 in-memory workloads such as SAP HANA, Oracle IMDB, and mission-critical virtualisation.
The R860 supports up to 24 × 2.5-inch SFF drives or 8 × EDSFF E3.S Gen 5 solid-state drives — high-speed storage positioned directly in front of four Xeon Scalable CPUs to minimise IO bottlenecks for database and analytics workloads.
The R860 supports 4th Gen Intel Xeon Scalable processors (Sapphire Rapids, LGA4677) in a quad-socket configuration with up to 60 cores per CPU — up to 240 total cores and 480 threads in a single chassis. Designed for Tier-1 ERP, mission-critical OLAP, and high-frequency trading platforms.
Yes. Express Computer Systems stocks professionally reconditioned Dell PowerEdge R860 rack servers tested and configured to your mission-critical specifications. Shop refurbished Dell R860 servers at ECS.
The R860 (Gen 16) replaces the R840 (Gen 14) — a two-generation leap. Key upgrades: 4th Gen Xeon Scalable (Sapphire Rapids) vs 2nd Gen (Cascade Lake-SP), DDR5 vs DDR4 with double the bandwidth, PCIe Gen 5.0 vs Gen 3.0, 16 TB RAM vs 6 TB, EDSFF E3.S Gen 5 drive support, and Intel in-die accelerators (AMX, DSA, QAT) plus iDRAC10 with OpenManage.
Ready to Deploy the Dell PowerEdge R860?
Express Computer Systems specializes in professionally refurbished Dell PowerEdge servers — tested, reconditioned, and ready for your most demanding business-critical workloads. Configure your R860 with the exact processor count, memory capacity, drive configuration, and PCIe riser layout for your environment.
Start building your custom server today