• Cisco Tesla T4 16GB GDDR6 PCIe 3.0 x16 low-profile GPU card
1 1

Cisco

Cisco UCSC-GPU-T4-16 | NVIDIA T4 GPU, 16GB GDDR6, 70W, PCIe 3.0 x16

UCSC-GPU-T4-16

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 We do not quote Gmail, Outlook or Hotmail addresses, or supply for home use. 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 UCSC-GPU-T4-16 delivers NVIDIA T4 GPU acceleration for Cisco UCS C-Series rack servers, powered by Turing Tensor Cores for AI inference, machine learning, and virtual desktop workloads. This low-profile, single-slot card features 16GB GDDR6 memory, 2,560 CUDA cores, and 320 Tensor Cores in an energy-efficient 70W design. Ideal for data centers requiring dense GPU compute in mainstream server environments.

Features

NVIDIA Turing architecture with dedicated Tensor Cores and RT Cores for accelerated AI and ray tracing
- Multi-precision computing: FP32, FP16, INT8, and INT4 support for diverse AI workloads
- 16GB GDDR6 memory with ECC for data integrity in production environments
- Low-profile, single-slot design for maximum server density and flexibility
- Passive cooling eliminates fan noise and enables quiet operation
- PCIe 3.0 x16 interface with 32 GB/sec interconnect bandwidth
- Hardware-accelerated video transcoding with dedicated encoding/decoding engines
- Up to 38 full-HD video stream decoding capability for video analytics
- NVIDIA vGPU support for virtual desktop infrastructure (VDI) and GPU virtualization
- TensorRT support for optimized deep learning inference deployment
- Energy-efficient 70W design reduces operational costs and cooling requirements
- Compatible with CUDA, TensorRT, ONNX, and other AI frameworks
- Designed for scale-out data center and cloud 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 Architecture: NVIDIA Turing
- Memory: 16GB GDDR6 with 300 GB/sec bandwidth
- CUDA Cores: 2,560
- Tensor Cores: 320
- Compute Performance: 8.1 TFLOPS (FP32), 65 TFLOPS (FP16/FP32 mixed), 130 TOPS (INT8), 260 TOPS (INT4)
- System Interface: PCIe 3.0 x16
- Interconnect Bandwidth: 32 GB/sec
- Form Factor: Low-profile PCIe, single-slot
- Thermal Solution: Passive cooling
- Power Consumption: 70W (typical), 75W (maximum)
- ECC Memory: Yes
- Compatible with: Cisco UCS C220 M5, C240 M5, C220 M6, and other UCS C-Series rack servers
- Compute APIs: CUDA, NVIDIA TensorRT, ONNX

FAQs

Q: What Cisco UCS servers are compatible with the UCSC-GPU-T4-16?
A: The UCSC-GPU-T4-16 is compatible with Cisco UCS C-Series rack servers including C220 M5, C240 M5, C220 M6, C240 M6, and related SmartPlay configurations. The C220 M6 can support up to three single-wide GPU cards in PCIe slots.

Q: What workloads is the NVIDIA T4 GPU optimized for?
A: The T4 is optimized for AI inference, deep learning training and inference, machine learning, data analytics, virtual desktop infrastructure (VDI), video transcoding (up to 38 full-HD streams), and high-performance computing workloads in data center and cloud environments.

Q: Does the T4 GPU support NVIDIA vGPU and virtualization?
A: Yes, the T4 supports NVIDIA GRID vGPU, GRID Virtual Workstation, and other virtualization features when licensed through the NVIDIA GRID License Server. This enables GPU virtualization for VDI and virtual workstation deployments.

Q: What are the power and cooling requirements?
A: The T4 has a typical power consumption of 70W with a maximum of 75W TDP. It uses passive cooling, making it suitable for high-density server deployments. The low power design allows multiple GPUs per server without excessive power or cooling infrastructure.

Q: What is the form factor and will it fit in standard servers?
A: The T4 is a low-profile, single-slot, half-height half-length (HHHL) PCIe card. This compact form factor is designed to fit easily into mainstream rack-mount servers and standard data center infrastructures without requiring specialized chassis.

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