Skip to product information
1 of 1

HPE

HPE S4A91C | NVIDIA H200 NVL 4-Way NVLink Bridge, Quad GPU

SKU:S4A91C

Request Quote
Sale Sold out
Shipping calculated at checkout.

Stock Status: Enquire

20-min response

Need a quote or bulk pricing? Answered within 20 minutes, Sydney business hours.

Description

This 4-way NVLink bridge is an NVIDIA accelerator option for HPE servers, designed to link four NVIDIA H200 NVL GPUs together. It suits AI training and inference, generative AI, large language models, computer vision, scientific discovery and financial modelling on HPE ProLiant Compute and HPE Cray systems fitted with NVIDIA accelerators.

The quad GPU, 4-way configuration connects four H200 NVL cards over NVLink so they can work together on large workloads. The bridge itself needs no licence. NVIDIA AI Enterprise licence activation is a separate consideration for H100 NVL and H200 NVL GPUs.

It is designed for NVIDIA H200 NVL GPUs in qualified HPE servers. NVIDIA Accelerators for HPE go through thermal, mechanical, power and signal integrity qualification in HPE servers, and the platform can be managed through HPE iLO.

Enquire with XS Network Tech for new or used pricing and availability.

Features

- Links four NVIDIA H200 NVL GPUs together over NVLink
- NVIDIA Accelerators for HPE go through thermal, mechanical, power and signal integrity qualification in HPE servers
- NVIDIA Qualified configurations are supported for production use
- Manageable through HPE iLO server management
- Suited to AI training, inference and generative AI workloads

Warranty

All products sold by XS Network Tech include a 12-month warranty on both new and used items. Our in-house technical team thoroughly tests used hardware prior to sale to ensure enterprise-grade reliability.

All technical data should be verified on the manufacturer data sheets.

View full details

specs-tabs

Collapsible content

Technical Specifications

FAQs

Technical Specifications

- Product type: NVLink bridge, server accelerator option
- Bridge configuration: 4-way (quad GPU)
- Designed for: NVIDIA H200 NVL GPUs
- Licensing: bridge itself needs no licence

FAQs

Q: Does the bridge need a licence?
A: No. The bridge itself needs no licence. NVIDIA AI Enterprise licence activation applies separately to H100 NVL and H200 NVL GPUs.

Q: Which GPUs is this bridge designed for?
A: It is designed for NVIDIA H200 NVL GPUs in qualified HPE servers.

Q: How many GPUs does it connect?
A: It is a 4-way bridge that links four GPUs in a quad GPU configuration.

Q: What workloads is it aimed at?
A: AI training and inference, generative AI, large language models, computer vision, scientific discovery and financial modelling on HPE systems with NVIDIA accelerators.

Recently Viewed

  • Request a Quote

    Looking for competitive pricing? Submit a request, and our team will provide a tailored quote that fits your needs.

  • Contact Us Directly

    Have a question or need immediate assistance? Call us for expert advice and real-time support.

    Call us Now  
  • Contact Us Directly

    Have a question or need immediate assistance? Call us for expert advice and real-time support.

    Contact us