// catalog / ai servers

GPU servers and AI systems

Integrated DGX systems, eight-GPU HGX platforms and 2U to 4U PCIe GPU servers from NVIDIA, Supermicro, Dell, Lenovo and HPE. Add a platform and quantity, note the configuration you want, and we reply with an all-in price and a delivery date.

Brand

8 of 8 products

NVIDIA

AI Servers

NVIDIA DGX H200

A fully integrated eight-GPU system delivered as one validated unit of hardware and software, for teams that want a supported reference platform rather than a custom build.

GPUs
8x NVIDIA H200 141GB
Total GPU memory
1,128GB
Processors
2x Intel Xeon Platinum 8480C

NVIDIA

AI Servers

NVIDIA DGX B200

Blackwell-generation integrated system for organisations planning new training capacity, with power and cooling needs that should be checked against the facility first.

GPUs
8x NVIDIA B200
Total GPU memory
1,440GB
Processors
2x Intel Xeon Platinum 8570

Supermicro

AI Servers

Supermicro SYS-821GE-TNHR

Air-cooled 8U platform built around an eight-GPU HGX baseboard with Intel host processors, widely used as a configurable alternative to integrated systems.

GPU support
NVIDIA HGX H100 or H200, 8-GPU
Processors
Dual 4th or 5th Gen Intel Xeon Scalable
Memory
32 DIMM slots, DDR5

Supermicro

AI Servers

Supermicro AS-8125GS-TNHR

The AMD-hosted counterpart of the 8U HGX platform, for estates that standardise on EPYC.

GPU support
NVIDIA HGX H200, 8-GPU
Processors
Dual AMD EPYC 9004 series
Memory
24 DIMM slots, DDR5

Dell

AI Servers

Dell PowerEdge XE9680

A 6U eight-way accelerator server offered with several GPU families, fitting organisations that already run PowerEdge tooling and support.

GPU support
8x SXM or OAM accelerators
Processors
Dual 4th or 5th Gen Intel Xeon Scalable
Memory
32 DIMM slots, DDR5

Dell

AI Servers

Dell PowerEdge R760xa

A 2U server for PCIe accelerators, a practical step for inference and mixed workloads before committing to eight-GPU nodes.

GPU support
Up to 4 double-width PCIe GPUs
Processors
Dual 4th or 5th Gen Intel Xeon Scalable
Memory
32 DIMM slots, DDR5

Lenovo

AI Servers

Lenovo ThinkSystem SR675 V3

A flexible 3U chassis that takes either PCIe cards or a four-GPU HGX board, useful where one platform has to serve several workload types.

GPU support
Up to 8 double-width PCIe GPUs, or HGX 4-GPU
Processors
1 or 2 AMD EPYC 9004 or 9005 series
Memory
24 DIMM slots, DDR5

HPE

AI Servers

HPE ProLiant DL380a Gen11

A GPU-dense take on the familiar 2U ProLiant, for teams that manage their fleet through iLO and want accelerators in the same operational model.

GPU support
Up to 4 double-width PCIe GPUs
Processors
Dual 4th or 5th Gen Intel Xeon Scalable
Memory
24 DIMM slots, DDR5

Before you order: AI Servers

The questions we ask before quoting. Answer them in the line notes and the first reply is usually the final one.

  • Eight-GPU systems can draw 10kW or more each. Confirm rack power, cooling and floor loading before anything else.
  • Most platforms are built to order. List the CPUs, memory, drives and network cards you want, or ask us to propose a balanced configuration.
  • Plan the fabric with the server: training clusters usually need one high-speed network port per GPU plus the switch ports to match.
  • Tell us the support level and response time you need. It is quoted as part of the system.

Specifications are indicative and confirmed on quote. Photos are representative of the hardware type, not the listed product. Product and brand names belong to their respective owners and are used for identification only.