• Samsung Galaxy S20 Ultra 5G with NVIDIA Ampere A10 GPU
1 1

NVIDIA

NVIDIA 900-2G133-0020-000 | A10 24GB GPU, 9216 CUDA, 150W Passive, PCIe 4.0

900-2G133-0020-000

Stock Status: Enquire

$5,388.90 inc. GST
$4,899.00 ex. GST
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 We do not quote Gmail, Outlook or Hotmail addresses, or supply for home use. 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 NVIDIA A10 Tensor Core GPU delivers enterprise-grade AI inference, virtual workstation graphics, and video processing for mainstream data center servers. Built on Ampere architecture with 24GB GDDR6 memory, 9216 CUDA cores, and 72 RT Cores in a power-efficient 150W passive design, it accelerates AI workloads, VDI deployments, rendering, and virtualized graphics across diverse professional applications. Compatible with NVIDIA vGPU software for scalable remote workstation environments.

Features

NVIDIA Ampere architecture with 2nd-gen RT Cores and 3rd-gen Tensor Cores
- 9216 CUDA cores for parallel compute and AI acceleration
- 24GB GDDR6 memory with 600 GB/s bandwidth for large models and datasets
- Hardware-accelerated ray tracing for photorealistic rendering
- Multi-Instance GPU (MIG) support for workload isolation and resource partitioning
- PCIe 4.0 x16 interface with 64 GB/s bidirectional bandwidth
- Single-slot passive design for maximum server density
- 150W TDP for power-efficient AI and graphics workloads
- NVIDIA vGPU software support for virtual desktop and application streaming
- Secure boot and hardware root-of-trust for firmware integrity
- AV1 decode acceleration for next-generation video streaming
- Multi-precision compute: FP32, TF32, FP16, BFLOAT16, INT8, INT4
- Sparsity acceleration for 2x performance on compatible AI models
- ECC memory support (enabled by default) for data integrity
- Headless operation optimized for remote workstation and VDI 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 Ampere (GA102)
- CUDA Cores: 9216
- Tensor Cores: 72 (3rd generation)
- RT Cores: 72 (2nd generation)
- GPU Memory: 24GB GDDR6
- Memory Interface: 384-bit
- Memory Bandwidth: 600 GB/s
- Memory Speed: 12.5 Gbps
- Base Clock: 885 MHz, Boost Clock: 1695 MHz
- FP32 Performance: 31.2 TFLOPS
- TF32 Tensor Core: 62.5 TFLOPS (125 TFLOPS with sparsity)
- FP16/BFLOAT16 Tensor Core: 125 TFLOPS (250 TFLOPS with sparsity)
- INT8 Tensor Core: 250 TOPS (500 TOPS with sparsity)
- INT4 Tensor Core: 500 TOPS (1000 TOPS with sparsity)
- Encode/Decode: 1x encoder, 2x decoder (with AV1 decode support)
- Interface: PCI Express 4.0 x16 (64 GB/s)
- Form Factor: Single-slot, full-height, full-length (FHFL)
- Cooling: Passive (fanless)
- TDP: 150W
- Power Connector: 1x 8-pin
- Display Outputs: Headless (no display connectors)
- vGPU Support: NVIDIA vPC, vApps, RTX vWS, Virtual Compute Server, AI Enterprise
- Secure Boot: Hardware root-of-trust with firmware attestation support

FAQs

Q: What workloads is the NVIDIA A10 optimized for?
A: The A10 is designed for AI inference, virtual desktop infrastructure (VDI), virtual workstations, rendering, and mixed graphics/AI workloads. It excels in data center environments requiring GPU virtualization, remote collaboration, and AI-accelerated design workflows.

Q: Does the A10 support NVIDIA vGPU software?
A: Yes, the A10 is fully compatible with NVIDIA Virtual PC (vPC), Virtual Applications (vApps), RTX Virtual Workstation (vWS), Virtual Compute Server, and AI Enterprise software, enabling flexible virtualized GPU deployments.

Q: What is the power and cooling requirement for this GPU?
A: The A10 has a 150W TDP and uses passive cooling (fanless). It requires a single 8-pin power connector and adequate server airflow for thermal management, making it suitable for high-density rack deployments.

Q: Is the A10 compatible with standard enterprise servers?
A: Yes, the A10 uses a standard PCIe 4.0 x16 interface and single-slot, full-height, full-length form factor. It is validated with major server platforms from Dell, HPE, Cisco, Lenovo, and other Tier-1 OEMs.

Q: Why is this GPU headless with no display outputs?
A: The A10 is designed for data center and virtualization workloads where graphics are streamed remotely via vGPU software. The headless design maximizes compute density and reduces cost, as direct display connectivity is not required in server environments.

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