• NVIDIA A2 Tensor Core GPU with gold case, 16GB GDDR6
1 1

NVIDIA

NVIDIA 900-2G179-0020-101-NQR | A2 Tensor Core GPU, 16GB GDDR6, PCIe 4.0 x8, 40-60W

900-2G179-0020-101-NQR

Stock Status: Enquire

Request Quote
Sale Sold out
Taxes included. Shipping calculated at checkout.

Description

The NVIDIA A2 Tensor Core GPU delivers entry-level AI inference acceleration in a compact, low-power design ideal for edge computing and intelligent video analytics deployments. Built on Ampere architecture with 16GB GDDR6 memory and 1280 CUDA cores, this single-slot, low-profile PCIe Gen4 x8 GPU provides up to 4.5 TFLOPS FP32 performance while operating within a configurable 40-60W thermal envelope. Passive cooling and NEBS-3 capability make it well-suited for challenging server environments requiring reliable AI acceleration at scale.

Features

NVIDIA Ampere Architecture with 3rd Generation Tensor Cores supporting INT4 to FP32 precision
- Automatic Mixed Precision (AMP) and TF32 support for AI training and inference acceleration
- 2nd Generation RT Cores for ray tracing acceleration (10 cores)
- Multi-Instance GPU (MIG) capability for workload isolation and resource partitioning
- Support for NVIDIA NGC catalog and optimized AI frameworks
- Sparsity acceleration delivering up to 2x performance improvement for sparse models
- AV1 hardware decode support plus H.264 and HEVC encode/decode
- PCIe 4.0 x8 interface for high-bandwidth connectivity to host CPU
- Single-slot, low-profile form factor compatible with compact servers and edge appliances
- Passive thermal solution with NEBS-3 capability for harsh environments
- vGPU software support enabling GPU virtualization and multi-tenant workloads
- Secure Boot with trusted code authentication and firmware rollback protection
- Error-Correcting Code (ECC) memory protection for data integrity
- GPU Direct RDMA support for direct memory access between GPUs and network adapters
- NVIDIA GPU Management and Monitoring tools (NVIDIA-SMI, DCGM) compatibility
- Support for CUDA, cuDNN, TensorRT, and comprehensive NVIDIA software stack

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 (GA107)
- GPU Memory: 16GB GDDR6
- Memory Interface: 128-bit
- Memory Bandwidth: 200 GB/s
- CUDA Cores: 1280
- Tensor Cores: 40 (3rd Generation)
- RT Cores: 10 (2nd Generation)
- Base Clock: 1440 MHz
- Boost Clock: 1770 MHz
- Peak FP32 Performance: 4.5 TFLOPS
- Peak FP16 Tensor Core: 18 TFLOPS (36 TFLOPS with sparsity)
- Peak INT8 Tensor Core: 36 TOPS (72 TOPS with sparsity)
- Peak INT4 Tensor Core: 72 TOPS (144 TOPS with sparsity)
- TF32 Tensor Core: 9 TFLOPS (18 TFLOPS with sparsity)
- Media Engines: 1x video encoder, 2x video decoders (includes AV1 decode)
- Interface: PCIe 4.0 x8
- Form Factor: Single-slot, low-profile (half-height, half-length)
- Thermal Design Power (TDP): 40-60W (configurable)
- Cooling: Passive (fanless, requires system airflow)
- Dimensions: 16.8 cm (depth) x 6.88 cm (height)
- Power Connector: No auxiliary power connector required
- Display Outputs: None (compute-focused GPU)
- Brackets Included: ATX full-height and low-profile brackets
- vGPU Software Support: NVIDIA vPC, vApps, RTX vWS, AI Enterprise, vCS
- Security Features: Secure Boot, firmware attestation, rollback protection (varies by CEC configuration)
- Standards Compliance: RoHS, NEBS-3 capable

FAQs

Q: What workloads is the NVIDIA A2 designed for?
A: The A2 is optimized for entry-level AI inference, intelligent video analytics, virtual desktop infrastructure, edge computing, machine learning inferencing, and video transcoding workloads. Its low power consumption and compact form factor make it ideal for deployment at scale in space-constrained server environments.

Q: Does the A2 require auxiliary power connectors?
A: No, the A2 draws all power through the PCIe 4.0 x8 slot and does not require auxiliary power connectors. Its configurable 40-60W TDP allows it to operate within standard PCIe power delivery limits.

Q: What is the difference between CEC and non-CEC versions?
A: The CEC (Confidential Computing Enablement Chip) provides an additional hardware root of trust for customers with high security requirements. Non-CEC versions (like the -101 SKU) still support Secure Boot, secure firmware updates, and rollback protection, but do not include key revocation or firmware attestation capabilities.

Q: Can the A2 be used for virtualized GPU workloads?
A: Yes, the A2 supports NVIDIA vGPU software including Virtual PC, Virtual Applications, RTX Virtual Workstation, AI Enterprise, and Virtual Compute Server, enabling multi-tenant GPU sharing and virtual desktop infrastructure deployments.

Q: What are the cooling requirements for the A2?
A: The A2 is a passively cooled, fanless GPU that relies entirely on system airflow for thermal management. Ensure adequate chassis ventilation and airflow to maintain proper operating temperatures. The card is NEBS-3 capable for challenging ambient environments.

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