Skip to product information
1 of 1

Cisco

Cisco HCI-GPU-A10-M6 | NVIDIA A10 GPU, 24GB GDDR6, PCIe Gen4, 150W Passive

SKU:HCI-GPU-A10-M6

Stock Status: Enquire

Request Quote
Sale Sold out
Shipping calculated at checkout.

Description

The Cisco HCI-GPU-A10-M6 is a data center GPU module featuring the NVIDIA A10 Tensor Core GPU with 24GB GDDR6 memory and 150W passive cooling. Built on NVIDIA Ampere architecture, it delivers powerful AI inference, rendering, and virtual workstation performance in a single-slot PCIe Gen4 form factor. Ideal for enterprise servers running virtualization, graphics-intensive VDI, and compute workloads in space-constrained data center environments.

Features

NVIDIA Ampere Architecture with 9216 CUDA Cores for versatile compute performance
- 24GB GDDR6 memory with ECC for reliable handling of large datasets
- 2nd Generation RT Cores (72 cores) for real-time ray tracing and graphics acceleration
- 3rd Generation Tensor Cores delivering 125 TFLOPS FP16 and 250 TOPS INT8 for AI workloads
- PCIe Gen 4.0 x16 interface with 64 GB/s bandwidth for fast data transfers
- Single-slot, full-height, full-length passive design for high-density deployments
- 150W TDP power envelope optimized for mainstream enterprise servers
- Hardware Root of Trust with secure and measured boot for firmware integrity
- NVIDIA vGPU support for multi-tenant virtual workstations and VDI
- Dual video decoders with AV1 support for advanced video processing
- 600 GB/s memory bandwidth across 384-bit bus for memory-intensive applications
- Support for NVIDIA CUDA-X libraries and NGC-optimized AI frameworks
- Compatible with VMware vSphere, Citrix Hypervisor, and KVM for flexible virtualization

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

GPU: NVIDIA A10 Tensor Core GPU (GA102-890)
- GPU Memory: 24GB GDDR6 with ECC
- Memory Bandwidth: 600 GB/s
- Memory Bus: 384-bit
- CUDA Cores: 9216
- Tensor Cores: 3rd Generation
- RT Cores: 2nd Generation, 72 cores
- Base Clock: 885 MHz, Boost Clock: 1695 MHz
- FP32 Performance: 31.2 TFLOPS
- Tensor Performance: 125 TFLOPS (FP16), 250 TOPS (INT8)
- Interface: PCIe Gen 4.0 x16 (64 GB/s bandwidth)
- Form Factor: Single-slot, full-height, full-length (FHFL), passive cooling
- TDP: 150W
- Power Connector: 8-pin PCIe power
- Encode/Decode: 1 encoder, 2 decoders (with AV1 decode support)
- vGPU Software Support: NVIDIA vPC, vApps, RTX vWS, vCS, AI Enterprise
- Secure Boot: Hardware Root of Trust enabled
- Compatible with Cisco UCS C-Series M6 and HyperFlex HX-Series M6 servers

FAQs

Q: What is the Cisco HCI-GPU-A10-M6 designed for?
A: This GPU module is designed for data center workloads including AI inference, virtual desktop infrastructure (VDI), graphics-rich virtual workstations, rendering, simulation, and GPU-accelerated compute. It is optimized for deployment in Cisco HyperFlex and UCS server environments.

Q: Does this GPU require active cooling?
A: No, the HCI-GPU-A10-M6 features passive cooling and relies on the server chassis airflow for thermal management. It must be installed in a compatible Cisco UCS C-Series M6 or HyperFlex HX-Series M6 server with adequate airflow.

Q: What virtualization technologies does the A10 support?
A: The NVIDIA A10 supports NVIDIA vGPU software, including vPC, vApps, RTX Virtual Workstation (vWS), Virtual Compute Server (vCS), and NVIDIA AI Enterprise, enabling multi-user GPU sharing and virtualized workloads across VMware, Citrix, and other hypervisors.

Q: What is the performance advantage over previous generation GPUs?
A: The A10 delivers up to 2.5x faster virtual workstation performance and inference throughput compared to the T4, with PCIe Gen 4.0 doubling the bandwidth over Gen 3 and 3rd-gen Tensor Cores providing significantly faster AI workload acceleration.

Q: Is this GPU compatible with all Cisco servers?
A: The HCI-GPU-A10-M6 is specifically designed for Cisco UCS C-Series M6 and HyperFlex HX240c/HX245c M6 servers with PCIe Gen4 riser support. It includes a unique SBIOS ID required by Cisco CIMC and UCSM for proper operation.

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