Uvation MarketplaceMarketplace

Dell Power Edge XE9785L AI Server

A 3 OU liquid-cooled AI server pairing eight NVLink-connected NVIDIA HGX B300 GPUs with dual Intel Xeon 6 processors for training, inference and HPC.

8x
GPUs
6 TB
Max RAM
33 kW
Power

Liquid-Cooled AI Density
in a 3OU Node

Eight NVLink-connected HGX B300 GPUs and dual AMD EPYC 9005 processors share a direct-to-chip liquid-cooled 3OU node built for ORv3 racks.

Dell PowerEdge XE9785L front view

Eight NVIDIA HGX B300 1200 W SXM7 GPUs, fully interconnected with NVLink, accelerate large-model training and inference.

Dual AMD EPYC 9005 processors with up to 192 cores each and up to 6 TB DDR5 keep GPUs fed.

A shared 33 kW rack power shelf with six 5500 W AC supplies feeds each node through DC busbar distribution.

Dell PowerEdge XE9785L front view

Dimensions & Weight

Engineered for ORv3 open rack standards with an optimized 3OU compute node footprint.

Dell PowerEdge XE9785L chassis
5.53 inches / 140.5 mm
Height
21.14 inches / 537 mm
Width
41.26 inches (with fans) / 1,047.95 mm with fans
Depth 889.65 mm (35.03 in) without
209.44 lbs / 95 kg
Weight

Enterprise Management Built In

Maximize cluster availability with iDRAC10, advanced out-of-band monitoring, Redfish API automation, and comprehensive OpenManage tooling.

Embedded / At-the-Server Management

iDRAC10 · iDRAC Direct · iDRAC RESTful API with Redfish · RACADM CLI · iDRAC Service Module

OpenManage Consoles

OpenManage Enterprise (OME) · OME Power Manager · OME Services · OME Update Manager · OME APEX AIOps Observability

Tools & Automation

IPMI · Red Hat Ansible Modules · Terraform Providers

Ports Overview

Network: 1 × OCP NIC 3.0 (x16 PCIe lanes) Front: 1 × USB 3.0 · 1 × Mini-DisplayPort · 1 × USB 2.0 Type-C · 2 × RJ45 dedicated iDRAC Ethernet Rear: N/A · Internal: 1 × USB 3.0 Note: all front ports are on the front I/O (FIO) board.

Direct-to-Chip Liquid Cooling

Direct-to-chip liquid cooling draws heat from the CPUs and 1200 W SXM7 GPUs, while supplemental fans cool auxiliary components, sustaining performance in dense ORv3 racks.

Dell PowerEdge XE9785L cooling and power
33 kW
Power shelf capacity
6x 5500W
AC power supplies

The rack, itemized

SUBSYSTEM

SPECIFICATION / CONFIGURATION DETAILS

Processor

Two 5th Generation AMD EPYC 9005 Series processors with up to 192 cores per processor

Operating System

Canonical Ubuntu Server LTS; Red Hat Enterprise Linux; SUSE Linux Enterprise Server

Chipset

N/A

Accelerators / GPU

8 × NVIDIA HGX B300 1200 W SXM7 GPUs with NVIDIA NVLink

Memory

24 DDR5 RDIMM slots; up to 6400 MT/s; maximum 6 TB

Primary Storage

16 x E1.S (122.88 TB); 8 x U.2 NVMe SSDs (245.76 TB)

Secondary Storage

Embedded BOSS: HWRAID 0/1, 2 x M.2 NVMe SSDs

Security

Signed firmware; Data-at-Rest Encryption (SEDs with local or external key management); Secure Boot; Secured Component Verification; Secure Erase; Silicon Root of Trust; System Lockdown; soldered TPM on Mezzanine DC-CSM; Chassis Intrusion Detection

Chassis

3OU compute sled for Dell IR7000 integrated rack

Power Supply

33 kW rack power shelf with 6 × 5500 W AC power modules; DC busbar distribution

Ports

1 x USB 3.0 Type-A port, 1 x Mini DisplayPort, 1 x USB 2.0 Type-C port, 2 x RJ45 dedicated iDRAC Ethernet port ; internal: 1 x USB 3.1 Type-A

Slots / PCIe Architecture

4 × PCIe Gen5 x16 FHHL slots for the B300 configuration

Bezel

Not available (NA)

Form Factor

3OU compute sled for IR7000 44OU rack

Network Card

1 x OCP NIC card 3.0 (x16 PCIe lanes)

Warranty

Dell Limited Hardware Warranty; ProSupport / ProSupport Plus Options, Duration Subject to Order

Nuclear-Ready, Plug and Play AI Factories

Bypass grid constraints with self-contained, high-density inference ready infrastructure directly adjacent to clean, base load nuclear power.

Global Deployment Engine

Any Infra, Anywhere in the world.

Global Shipping and Deployment Capability treats advanced infrastructure as mobile, modular freight.

Packaged complex computing nodes, cooling manifolds, and power distribution units into certified, standard form factors.

360° Service Ecosystem

Unifying Legacy with Next-Gen Compute.

Vertically integrated service ecosystem that serves as an operational bridge between legacy environments and next-generation, AI-native infrastructure.

Finance and Leasing

Capital-as-a-Service for High-Density Compute

Convert upfront capital expenditures (CapEx) into predictable operating expenses (OpEx).

Uvation allows enterprises and sovereign entities to deploy multi-megawatt AI factories and advanced GPU clusters without liquidity constraint.