• Cisco UCSX-GPU-A16-D A16 gold NVIDIA GPU card, 64GB GDDR6, 250W
1 1

Cisco

Cisco UCSX-GPU-A16-D | NVIDIA A16 GPU, 64GB GDDR6, 4x 16GB, 250W Passive

UCSX-GPU-A16-D

Stock Status: Enquire

Request Quote
Sale Sold out
Shipping calculated at checkout.

 Trade supply only. Server & GPU quote requests need a company name, ABN and work email address. We do not quote Gmail, Outlook or Hotmail addresses, or supply for home use. 

20-min response

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

Custom Built Servers

Need a different spec, quantity or configuration?

We build configured-to-order refurbished servers from Cisco, Dell, HPE, NVIDIA Lenovo and Supermicro. Tell us what you need and we'll come back with options within 24 hours.

Configure your server now →

Description

The Cisco UCSX-GPU-A16-D is a server-optimized NVIDIA A16 GPU accelerator designed for high-density virtual desktop infrastructure deployments. Featuring a unique quad-GPU architecture with 64GB total GDDR6 memory across four independent 16GB GPUs, it delivers exceptional user density for graphics-rich VDI environments powered by NVIDIA Virtual PC or RTX Virtual Workstation software. Built on NVIDIA Ampere architecture with passive cooling, it integrates seamlessly into Cisco UCS X-Series and C-Series platforms for enterprise virtualization workloads.

Features

NVIDIA Ampere architecture with 2nd-gen RT Cores and 3rd-gen Tensor Cores
- Quad-GPU board design with four independent 16GB GDDR6 GPUs for flexible user provisioning
- Optimized for high-density VDI with up to 64 concurrent users per board
- Delivers 2x user density compared to previous-generation VDI GPUs
- Support for NVIDIA Virtual PC, RTX Virtual Workstation, and AI Enterprise software
- Hardware-accelerated H.264 and H.265 video encode/decode engines per GPU
- ECC memory support for data integrity in professional workloads
- PCIe Gen4 x16 interface for high-bandwidth connectivity
- Passive thermal solution optimized for data center server environments
- Secure Boot, firmware attestation, and hardware root of trust security features
- Mixed workload support: virtual desktops, virtual workstations, and AI inference on a single card
- Low-latency virtual desktop experience indistinguishable from native PC performance
- Large per-user framebuffer enabling entry-level CAD and design applications
- NVIDIA GPU management and monitoring tools for virtualized environments
- Certified for Cisco UCS X-Series modular systems and C-Series rack servers

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 A16 quad-GPU design (4x independent GPUs per board)
- Memory: 64GB total GDDR6 (4x 16GB per GPU)
- Memory Bandwidth: 800 GB/s total (4x 200 GB/s per GPU)
- CUDA Cores: 5,120 total (1,280 per GPU)
- Tensor Cores: 160 total (40 per GPU, 3rd generation)
- RT Cores: 40 total (10 per GPU, 2nd generation)
- Architecture: NVIDIA Ampere
- Interface: PCIe Gen4 x16
- Power Consumption: 250W TDP
- Cooling: Passive, server-optimized thermal solution
- Form Factor: Dual-slot FHFL (Full-Height, Full-Length)
- Applications: VDI, virtual desktops, virtual workstations
- Software Compatibility: NVIDIA vPC, vWS, vApps, AI Enterprise
- Included: PCIe power cable
- Platform Support: Cisco UCS X-Series (UCSX-GPU-A16), UCS C-Series (UCSC-GPU-A16-D)

FAQs

Q: What is the primary use case for the NVIDIA A16 GPU?
A: The A16 is purpose-built for high-density virtual desktop infrastructure deployments. It supports graphics-rich virtual PCs for knowledge workers and entry-level virtual workstations for CAD and design applications, enabling up to 64 concurrent users per board when paired with NVIDIA vGPU software.

Q: How does the quad-GPU design benefit VDI deployments?
A: The unique quad-GPU architecture with four independent 16GB GPUs allows IT administrators to provision mixed user profiles on a single board. You can assign separate GPUs to different workload types—such as standard virtual PCs, power users, or virtual workstations—providing flexible resource allocation and maximizing hardware utilization.

Q: Which Cisco UCS platforms are compatible with the A16 GPU?
A: The UCSX-GPU-A16-D is designed for Cisco UCS X-Series modular systems, including X210c M6/M7 and X410c M7 compute nodes with X440p PCIe nodes. Cisco also offers the UCSC-GPU-A16-D variant for UCS C-Series rack servers such as the C240 M7. Verify compatibility with your specific server model and riser configuration.

Q: What software licenses are required to use the A16 GPU?
A: The A16 requires NVIDIA vGPU software licenses for virtualization features. NVIDIA Virtual PC licenses enable graphics-accelerated virtual desktops for knowledge workers, while NVIDIA RTX Virtual Workstation licenses support professional applications like CAD. NVIDIA AI Enterprise is available for AI and compute workloads on unused VDI resources.

Q: What are the power and cooling requirements?
A: The A16 has a 250W TDP and uses passive cooling, relying on server-level airflow and thermal management. Ensure your Cisco UCS chassis or rack server has adequate cooling capacity and PSU headroom. The card requires PCIe Gen4 x16 connectivity and includes the necessary power cable for installation.

Related Products

View all Graphics Card | GPU

  • 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