Skip to content
Home / GPU Servers / RDP GX8 HGX 8-GPU Server
Make in India
GPU ServersFlagship · Scale

RDP GX8 HGX 8-GPU Server

8-GPU HGX baseboard for serious training — 70B–405B at scale, NVIDIA-Certified and Make-in-India.

Made to order
Price on application
Configured to your fabric · financing & GPU-as-a-Service
  • Architect-validated config & cluster reference design
  • INR pricing · GST · available on GeM
  • 3-year pan-India onsite SLA & install
Same-day response from a solution architect
Key specifications
Full spec sheet ↓
GPUs8× NVIDIA H100 80GB SXM5 (HGX)
GPU memory640 GB HBM3
Model fit70B–405B
CPU2× Intel Xeon Platinum 8568Y+
System memory2 TB DDR5 ECC (up to 4 TB)
Storage2× 1.92 TB NVMe + 8× 3.84 TB NVMe
Networking8× 400G InfiniBand + 2× 100G
Chassis5U rackmount · Air or direct liquid (DLC)

Overview

RDP GX8 HGX 8-GPU Server is a flagship HGX baseboard system for large-model training — the training workhorse of the GPU Servers range and the building block of a multi-node GPU cluster.

Eight NVSwitch-connected H100 SXM GPUs and 640 GB HBM3 train and fine-tune 70B–405B models on a single node, and scale out over a 400G InfiniBand fabric.

Key specifications

GPUs8× NVIDIA H100 80GB SXM5 (HGX)
GPU memory640 GB HBM3
GPU interconnectNVSwitch (900 GB/s all-to-all)
CPU2× Intel Xeon Platinum 8568Y+
System memory2 TB DDR5 ECC (up to 4 TB)
Storage2× 1.92 TB NVMe + 8× 3.84 TB NVMe
Networking8× 400G InfiniBand + 2× 100G
CoolingAir or direct liquid (DLC)
Form factor5U rackmount
Power6× 3000W redundant (3+3)
ManagementBMC · Redfish · IPMI 2.0
OS / stackUbuntu 22.04, RHEL 9 · NVIDIA AI Enterprise

Spec values are representative for this preview and bind to the corrected live product data at wiring.

Workload fit

70B–405B training and large-scale fine-tuning on a single node, and the unit cell of a multi-node GPU cluster over the 400G InfiniBand fabric.

Why RDP GPU Mart

  • Make in India OEM — 28,000 sq ft Hyderabad facility, 14 years, 300,000+ devices shipped.
  • Sovereign-ready: India data residency (DPDP), MeitY-recognised, ISO 27001 / SOC 2 paths.
  • INR-transparent: GST invoice, HSN 8471, CGST/SGST or IGST, pan-India onsite SLA.
  • Available on GeM for government and PSU procurement.

FAQ

How is it billed and supported?

INR with GST (HSN 8471), CGST/SGST or IGST by state, EMI/lease/GPUaaS options, and 3-year pan-India onsite support. Available on GeM.

Can I start as a pilot and scale to a cluster?

Yes — the fabric and management stack let you add nodes and a head node later. Talk to an architect for the reference design.

What software stack is included?

Ubuntu 22.04 / RHEL 9 with NVIDIA AI Enterprise, drivers and CUDA validated; Slurm/Kubernetes on request.

Compare the range

Other GPU Servers in this line

GX4 4-GPUGX4 PlusGX4 MaxGX8 HGX
GPUs4× L40S4× H100 PCIe4× H100 SXM8× H100 SXM
Model fitup to 34B34B–70B70B70B–405B
CoolingAirAirAir / DLCDirect liquid
PricePrice on requestPrice on requestRequest a QuoteOn request
ViewViewViewQuote
Build the full stack

Pair it with

Designing a GPU cluster, not just one server?

Talk to our solution architects — multi-node fabric design, financing & GPU-as-a-Service, India-onsite SLA.

Talk to a solutions architect