1 1

Cisco

Cisco UCSXE-GPU-L4 | NVIDIA L4 24GB GPU, 70W, HHHL, PCIe Gen4 x16

UCSXE-GPU-L4

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

The NVIDIA L4 Tensor Core GPU is a low-profile, single-slot accelerator based on the Ada Lovelace architecture, supplied as a GPU option for Cisco UCS X-Series compute environments. It suits AI inference and generative AI, video transcoding and streaming, virtual desktops and workstations, graphics and rendering, and edge deployments where power and space are limited.

This variant carries 24GB of GDDR6 memory with 300 GB/s of memory bandwidth and connects over a PCIe Gen4 x16 interface rated at 64GB/s. It sits in the 70W power class, with NVIDIA listing a maximum thermal design power of 72W, in a 1-slot half-height, half-length form factor. Performance figures include 30.3 TFLOPS of FP32 and 485 TFLOPS of FP8 Tensor Core throughput with sparsity. Media hardware comprises 2 NVENC encoders, 4 NVDEC decoders and 4 JPEG decoders.

The card needs no licence to operate. NVIDIA vGPU software and NVIDIA AI Enterprise are optional licence add-ons for virtualisation and enterprise AI software.

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

Features

- Fourth-generation Tensor Cores with FP8 support and structured sparsity for AI inference and generative AI
- Third-generation RT Cores and DLSS 3 for ray tracing and graphics workloads
- Optimised AV1 stack with video encoders and decoders for transcoding, streaming and video conferencing
- Up to 120X higher AI video performance than CPU-only servers (NVIDIA-measured)
- Virtualisation-ready with NVIDIA vGPU software (RTX vWS, vPC)
- Secure boot with root-of-trust
- Energy-efficient single-slot low-profile design suited to edge deployments

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 L4 Tensor Core (Ada Lovelace)
- GPU memory: 24GB GDDR6
- Memory bandwidth: 300 GB/s
- Power class: 70W
- Maximum thermal design power: 72W
- Interface: PCIe Gen4 x16, 64GB/s
- Form factor: 1-slot low-profile (HHHL)
- FP32: 30.3 TFLOPS
- TF32 Tensor Core: 120 TFLOPS (with sparsity)
- FP16 Tensor Core: 242 TFLOPS (with sparsity)
- BFLOAT16 Tensor Core: 242 TFLOPS (with sparsity)
- FP8 Tensor Core: 485 TFLOPS (with sparsity)
- INT8 Tensor Core: 485 TOPS (with sparsity)
- NVENC | NVDEC | JPEG decoders: 2 | 4 | 4
- Server options: Partner and NVIDIA-Certified Systems with 1-8 GPUs

FAQs

Q: Does the NVIDIA L4 GPU need a licence to operate?
A: No. The hardware operates without a licence. NVIDIA vGPU software and NVIDIA AI Enterprise are optional licence add-ons for virtualisation and enterprise AI software.

Q: How is the card powered?
A: It belongs to the 70W power class, with a maximum thermal design power of 72W listed by NVIDIA. It is powered through the PCIe slot and does not need a separate GPU power cable.

Q: What platform does it work with?
A: It is a GPU option for the Cisco UCS X-Series platform. Confirm node and riser support for your configuration against the relevant Cisco spec sheet.

Q: What workloads is the L4 suited to?
A: It targets AI inference and generative AI, video transcoding and streaming, virtual desktops and workstations with vGPU, graphics and rendering, and edge deployments.

Q: How does this variant differ from other L4 listings?
A: This is the 24GB, 70W, single-slot HHHL version with a PCIe Gen4 x16 interface.

Related Products

View all Graphics Card | GPU

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