• NVIDIA Jetson Xavier NX Dev Kit with 6-core Carmel CPU and 8GB RAM
1 1

NVIDIA

NVIDIA 900-83668-0000-000 | Jetson Xavier NX AI Module, 6-Core Carmel, 384-Core Volta GPU, 8GB LPDDR4x, 16GB eMMC

900-83668-0000-000

Stock Status: Enquire

$1,004.41 inc. GST
$913.10 ex. GST
Sale Sold out
Taxes included. Shipping calculated at checkout.

Description

The NVIDIA Jetson Xavier NX Module delivers up to 21 TOPS of AI performance in a compact credit card-sized system-on-module. Designed for embedded and edge AI applications, it features a 6-core Carmel ARM CPU, 384-core Volta GPU with 48 Tensor Cores, 8GB LPDDR4x memory, and 16GB integrated eMMC storage. Ideal for autonomous machines, industrial robotics, smart cameras, and AIoT devices requiring high-performance inference in power-constrained environments.

Features

NVIDIA Volta GPU with 384 CUDA cores and 48 Tensor Cores for accelerated AI inference
- 6-core Carmel ARM v8.2 64-bit CPU with dual-issue 10-wide superscalar architecture
- Dual NVDLA (Deep Learning Accelerator) engines for efficient neural network processing
- 51.2GB/s memory bandwidth from 128-bit LPDDR4x for high-throughput workloads
- Hardware-accelerated encode/decode for H.265, H.264, VP9 video formats
- Support for multiple concurrent neural networks and multi-sensor data fusion
- Software-defined power modes for flexible performance and power optimization
- 260-pin SO-DIMM edge connector for easy integration into custom carrier designs
- Extended temperature range operation from -25°C to 80°C for industrial environments
- Full JetPack SDK support with CUDA, TensorRT, cuDNN, and OpenCV acceleration
- Compatible with NVIDIA NGC pre-trained models and Transfer Learning Toolkit
- Cloud-native deployment support with containerized application frameworks

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: 384-core NVIDIA Volta architecture with 48 Tensor Cores
- CPU: 6-core NVIDIA Carmel ARM v8.2 64-bit processor
- AI Performance: Up to 21 TOPS at 15W, 14 TOPS at 10W
- Memory: 8GB 128-bit LPDDR4x, 51.2GB/s bandwidth
- Storage: 16GB eMMC 5.1
- AI Accelerators: 2x NVDLA engines, 7-way VLIW vision processor
- Video Encode: 2x 4K30 (H.265), 4x 1080p60 (H.265)
- Video Decode: 2x 4K60 (H.265), 4x 4K30 (H.265), 8x 1080p60 (H.265)
- Form Factor: 69.6mm x 45mm system-on-module
- Power Modes: Configurable 10W and 15W profiles
- Operating Temperature: -25°C to 80°C (extended)
- Supported Software: NVIDIA JetPack SDK, CUDA, TensorRT, cuDNN

FAQs

Q: What is the difference between the module and the developer kit?
A: The 900-83668-0000-000 is the production module only, containing the SOM with 16GB eMMC. It requires a separate carrier board for operation. The developer kit (SKU 945-83518-0005-000) includes the module, reference carrier board with I/O ports, power supply, and uses microSD storage instead of eMMC.

Q: What carrier boards are compatible with this module?
A: The Jetson Xavier NX module is compatible with the official NVIDIA developer kit carrier board, Jetson Nano developer kit B01 carrier board, and numerous third-party carrier boards from manufacturers like Connect Tech, Auvidea, and Seeed Studio designed for the 260-pin SO-DIMM form factor.

Q: What AI frameworks and software does this module support?
A: The module supports NVIDIA JetPack SDK with comprehensive libraries including CUDA, cuDNN, TensorRT for inference acceleration, VisionWorks for computer vision, and popular frameworks such as TensorFlow, PyTorch, Caffe, and ONNX Runtime. Cloud-native containerized deployment is also supported.

Q: What are typical applications for the Xavier NX module?
A: Common deployments include autonomous mobile robots, industrial inspection systems, smart cameras with on-device AI, medical imaging devices, retail analytics, agricultural automation, intelligent transportation systems, and other edge AI applications requiring high inference performance in compact, power-efficient form factors.

Q: How does the 10W mode compare to the 15W mode?
A: In 10W mode, the module delivers up to 14 TOPS by limiting CPU and GPU frequencies and core counts, ideal for battery-powered or thermally constrained applications. The 15W mode unlocks full performance at up to 21 TOPS by utilizing all 6 CPU cores and maximum GPU clock speeds.

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