Skip to product information
1 of 1

NVIDIA

NVIDIA 900-82888-0040-000 | AGX Xavier Dev Kit | 8-core ARMv8 (Carmel), Volta 512-core GPU + 64 Tensor Cores, 32GB LPDDR4x, 32GB eMMC, GbE, USB 3.1, M.2 NVMe, MIPI CSI-2, HDMI/DP

SKU:900-82888-0040-000

Regular price POA
POA
POA
Sale Sold out
Shipping calculated at checkout.

Description

High-performance edge AI development platform built on an 8-core ARMv8 CPU and Volta GPU with Tensor Cores for accelerated inferencing. Includes a full-featured carrier with GbE, USB 3.1, display outputs, M.2 expansion, and multi-camera interfaces to speed prototyping and deployment.

Features

- Volta GPU with Tensor Cores for high-throughput deep learning inference
- Rich I/O: multi-camera CSI-2, USB 3.1, NVMe, and display outputs
- Production-aligned SOM enables straightforward path from prototype to deployment
- JetPack SDK ecosystem with CUDA and TensorRT acceleration
- Compact, power-efficient edge AI compute

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
  • You may also like
  • Best sellers
  • Related Products

specs-tabs

Collapsible content

FAQs

Technical Specifications

FAQs

Q: Does this include the carrier board and power supply?
A: Yes, as a developer kit it includes the SOM pre-installed on a carrier board; included accessories vary by kit revision and region.

Q: Which operating system is supported?
A: Runs NVIDIA JetPack (Linux for Tegra based on Ubuntu), with support for CUDA, cuDNN, TensorRT, and related SDKs.

Q: Can I add NVMe storage?
A: Yes, the carrier provides an M.2 Key M slot for NVMe SSDs.

Q: How many cameras can I connect?
A: The platform supports multiple MIPI CSI-2 cameras; exact channel count depends on the carrier board and sensor configuration.

Q: Is PoE supported on the Ethernet port?
A: No, Ethernet is standard GbE; PoE would require an external injector/splitter or a PoE-capable carrier.

Technical Specifications

- SoC/CPU: 8-core 64-bit ARMv8 (Carmel)
- GPU: 512-core Volta with 64 Tensor Cores
- AI performance: up to 32 TOPS (INT8, typical for platform class)
- Memory: 32GB LPDDR4x
- Storage: 32GB eMMC onboard; M.2 Key M slot for NVMe SSD
- Networking: 10/100/1000 Mbps Ethernet
- I/O: USB 3.1, USB-C, M.2 (Key M/Key E), GPIO, I2C, SPI
- Camera: Multiple MIPI CSI-2 lanes for multi-camera input
- Display: HDMI/DisplayPort (carrier-dependent)
- Software: JetPack SDK (L4T/Ubuntu), CUDA, cuDNN, TensorRT, DeepStream
- Form factor: SOM + developer carrier board with active cooling
- Use cases: Robotics, machine vision, edge AI, autonomous machines

Recently Viewed

  • Request for 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