• Sleek gold Cisco UCSX-GPU-L40S laptop sleeve with black accents
1 1

HPE

HPE S2L70C | NVIDIA L40S 48GB GDDR6 PCIe Gen4 GPU Accelerator

S2L70C

Stock Status: Enquire

Request Quote
Sale Sold out
Shipping calculated at checkout.
20-min response

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

Description

This NVIDIA L40S 48GB GDDR6 accelerator is a dual-slot PCIe Gen4 x16 GPU built on the Ada Lovelace architecture for data centre deployment. It is qualified for HPE mainstream compute platforms and suits generative AI, inference, graphics and virtualisation workloads. With 864 GB/s of memory bandwidth and a passively cooled, full-height full-length design, it integrates into supported HPE servers for multi-GPU and multi-node configurations.

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

Features

- NVIDIA qualified for thermal, mechanical, power and signal integrity on HPE servers
- Supported in NVIDIA-Certified HPE servers, tested for multi-GPU and multi-node performance
- HPE Integrated Lights-Out (iLO) management for configuring, monitoring and updating the accelerator
- Silicon Root of Trust security via iLO
- Passively cooled data centre design

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

Technical Specifications

FAQs

Technical Specifications

- GPU: NVIDIA L40S (Ada Lovelace)
- Memory: 48GB GDDR6
- Memory bandwidth: 864 GB/s
- System interface: PCIe Gen4 x16
- Power: 275W
- Form factor: dual-slot, full-height full-length, 4.4"H x 10.5"L
- Dimensions: 3.47 x 26.7 x 11.1 cm
- Performance: 90 TFLOPS FP32
- FP8 Tensor performance: 1,466 TFLOPS (with sparsity)
- Supported platforms: HPE mainstream compute platforms
- Cooling: passive

FAQs

Q: What workloads is the NVIDIA L40S 48GB accelerator designed for?
A: It targets generative AI, inference, graphics and virtualisation workloads in data centre environments, using 48GB of GDDR6 memory and the Ada Lovelace GPU architecture.

Q: What PCIe interface and form factor does it use?
A: It uses a PCIe Gen4 x16 interface in a dual-slot, full-height full-length form factor measuring 4.4"H x 10.5"L.

Q: How is this accelerator cooled?
A: It is a passively cooled design, so the host server must provide adequate front-to-back airflow across the card.

Q: Can it be managed through HPE iLO?
A: Yes. HPE Integrated Lights-Out (iLO) can be used to configure, monitor and update the accelerator, and Silicon Root of Trust security is supported via iLO.

Q: Which servers is this accelerator intended for?
A: It is supported on HPE mainstream compute platforms and in NVIDIA-Certified HPE servers, where it has been tested for multi-GPU and multi-node performance.

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