Skip to product information
1 of 1

HPE

HPE S3U30C | NVIDIA H200 NVL 141GB HBM3e PCIe Gen5 GPU Accelerator

SKU:S3U30C

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

The NVIDIA H200 NVL is a PCIe Gen5 data-centre GPU accelerator card supplied by HPE. It carries a single NVIDIA H200 Tensor Core GPU with 141 GB of HBM3e memory, and is aimed at generative AI, large language model inference and high-performance computing workloads.

The headline numbers for this card are the 141 GB of HBM3e memory per board and 4.8 TB/s of memory bandwidth. Larger and faster memory lets bigger models sit on a single accelerator, which suits high-performance LLM inference. The host interface is PCI Express 5.0, and the card can be managed through HPE Integrated Lights-Out (iLO) in supported HPE servers.

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

Features

- Single NVIDIA H200 Tensor Core GPU per card
- 141 GB of HBM3e memory for large generative AI models
- 4.8 TB/s memory bandwidth for data-intensive workloads
- PCIe Gen5 host interface
- Suited to high-performance LLM inference and HPC
- HPE iLO management integration

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

- Accelerators per card: 1 x NVIDIA H200 Tensor Core GPU
- Memory size per board: 141 GB HBM3e
- Memory bandwidth: 4.8 TB/s
- Host interface: PCI Express 5.0
- Accelerator application: High-performance LLM inference
- Management: HPE Integrated Lights-Out (iLO)

FAQs

Q: What workloads is the H200 NVL designed for?
A: It is aimed at generative AI, large language model inference and high-performance computing. The 141 GB of HBM3e memory and 4.8 TB/s bandwidth are targeted at memory-intensive inference workloads.

Q: What host interface does this accelerator use?
A: It uses a PCI Express 5.0 interface, so it needs a server with a suitable PCIe Gen5 slot.

Q: Can it be managed through HPE iLO?
A: Yes. The card supports management through HPE Integrated Lights-Out (iLO) when installed in a supported HPE server.

Q: How much memory does each card have?
A: Each card has 141 GB of HBM3e memory with 4.8 TB/s of memory bandwidth.

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