reComputer Mini J4012 NVIDIA Jetson Orin NX 16GB Extension

Description

reComputer Mini J4012 NVIDIA Jetson Orin NX 16GB Extension

reComputer Mini J4012 with extension is a tiny AI computer powered by NVIDIA® Jetson Orin™ NX 16GB module, delivering up to 100 TOPS AI performance. It‘s equipped with PCIe port at the bottom to provide rich expansion capabilities, including up to 8 USB ports and dual CAN, which also can be customized flexibly. The whole system is designed for embedding into autonomous machines such as drones, patrol robots, delivering robots, etc. It can directly occupy 54V DC input, able to be widely used in battery powered systems.

  • Brilliant AI Performance for Production: Achieves up to 100 TOPS AI performance with low power and latency, built by NVIDIA Orin SoC combining the NVIDIA Ampere™ GPU architecture with 64-bit operating capability, integrated advanced multi-function video and image processing, and NVIDIA Deep Learning Accelerators.
  • Hand-Size Edge AI Device: Compact size at 63mm x 95mm x 66.7mm, featuring an NVIDIA Jetson Orin NX 16GB module, Mini J401 carrier board, fan and enclosure. Support desktop and wall mounting.
  • Expandable with Rich I/Os: Includes up to 8x USB, DP 1.4, 1x RJ45 for GbE, M.2 Key E, M.2 Key M, dual channel CAN, and GPIO.
  • Accelerate Solutions to Market: Pre-installed JetPack 6.0 on 128GB NVMe SSD, Linux OS BSP, supporting Jetson software and leading AI frameworks.
  • Scale to deploy: support OTA, remote management services powered by Allxon and Balena.
  • Flexible Customization: inlcudes changing accessories modules, logo, and hardware interfaces modification based on reComputer Mini J4012 original design.

Specification

Jetson Orin System on Module

AI Performance

reComputer Mini J4012 with Extension - Orin NX 16GB, 100 TOPS

reComputer Mini J3011 with Extension - Orin Nano 8GB – 40 TOPS

GPU

1024-core NVIDIA Ampere architecture GPU with 32 Tensor Cores

CPU

8-core Arm® Cortex®-A78AE v8.2 64-bit CPU (Orin NX 16GB)

6-core Arm® Cortex®-A78AE (Orin Nano 8GB)

Memory

16GB 128-bit LPDDR5 (Orin NX 16GB)

8GB 128-bit LPDDR5 (Orin NX 8GB)

Video Encode

1x 8K30 (H.265) | 2x 4K60 (H.265) | 4x 4K30 (H.265) | 9x 1080p60 (H.265) | 18x 1080p30 (H.265)

1080p30 supported by 1-2 CPU cores

Video Decode

1x 8K30 (H.265)

2x 4K60 (H.265)

4x 4K30 (H.265)

9x 1080p60 (H.265)

18x 1080p30 (H.265)

1x 4K60 (H.265)

2x 4K30 (H.265)

5x 1080p60 (H.265)

11x 1080p30 (H.265)

DL Accelerator

2x NVDLA v2

/

Carrier Board

Storage

1x M.2 Key M PCIe (M.2 NVMe 2242 SSD 128G included)

Networking

M.2 KEY E

1x M.2 Key E for WiFi/Bluetooth module

I/O

USB

2x USB 3.2 Type-A (10Gbps);

1x USB 2.0 Micro-B (Device Mode);

1x USB 3.2 Type-C (Host Mode);

1x USB 2.0 JST-5pin (Host Mode);

UART

1x UART

1x Debug Uart

Display

1x DP 1.4 (included in Type-C conenctor)

Fan

1x 4 pin Fan Connector (5V PWM)

Button

1x Reset Button; 1x Recovery Button

Extension Port

2x 60 pin High Speed Connector (For extension board)

1x 10 pin Power Connector (For extension board)

RTC

1x RTC 2-pin

Power

1 x XT30 Connector (12-54V DC)

Extension Board

Networking

Ethernet

1x RJ-45 Gigabit Ethernet (10/100/1000M)

I/O

USB

4 x USB 3.0 Type-A (5 Gbps)

CAN

1 x CAN JST 4pin (5V)

1 x CAN (XT30 2+2)

FAN

1x 4 pin Fan Connector (5V PWM)

I2C

2 x I2C JST 4pin (3.3V)

SPI

1 x SPI JST 6pin (3.3V)

Power

2 x XT30(2+2) Connector (12-54V DC)

Mechanical

Dimensions (W x D x H)

63mm x 95mm x 42mm (Without Extension)

63mm x 95mm x 66.7mm (With Extension)

Weight

345g (Without Extension)

462g (With Extension)

Installation

Desk, Wall-mounting

Operating Temperature

-10℃~50℃

Warranty

1 Year

Hardware Overview

● Desktop, wall Mount, expandable, or fit in anywhere


Application

● Robotic Control

  • Capable of Bringing Generative AI to the Edge

Now you can build AI agents capable of processing large amounts of live or archived videos and images with Vision-Language Models (VLM) such as LLaVA, this new AI agents help nearly every industry summarize, search, and extract actionable insights from video using natural language.

  • Build Multi-streams AI Video Analytics

For building video analytics, Jetson Orin NX incorporates the NVIDIA Multi-Standard Video Decoder. This video decoder accelerates video decode, supporting low resolution mobile content, Standard Definition (SD), High Definition (HD) and UltraHD (8K, 4K, etc.) reComputer J4012 can take 18x1080p30 streams. See our tested YOLOv8 performance using NVIDIA Deepstream of single model and multi model on multi streams.

  • Fastest Way to Deploy Generative AI and Computer Vision Models

We have jetson-example prepared for you! It offers one-line deploy projects edge AI applications of generative AI including Ollama, Llama3; computer vision including YOLOv8; and others. We have configured all environment for you to provides single command deployment of projects.


Read more

reComputer Mini J4012 NVIDIA Jetson Orin NX 16GB Extension

Product form
Free pickup in our shop(s)

SKU: 102111001

$1,649.00 $1,549.00 Excl. GST

$1,549.00
Product available in stock.

    • We ship from our stock in AU (Perth), pickup by prior booking
    • We Offer Quantity Discounts for Large Orders 10+ qty (Request Quote)
    • We accept Purchase Orders & Net 30-day Payment for Eligible Accounts

    Description

    reComputer Mini J4012 NVIDIA Jetson Orin NX 16GB Extension

    reComputer Mini J4012 with extension is a tiny AI computer powered by NVIDIA® Jetson Orin™ NX 16GB module, delivering up to 100 TOPS AI performance. It‘s equipped with PCIe port at the bottom to provide rich expansion capabilities, including up to 8 USB ports and dual CAN, which also can be customized flexibly. The whole system is designed for embedding into autonomous machines such as drones, patrol robots, delivering robots, etc. It can directly occupy 54V DC input, able to be widely used in battery powered systems.

    • Brilliant AI Performance for Production: Achieves up to 100 TOPS AI performance with low power and latency, built by NVIDIA Orin SoC combining the NVIDIA Ampere™ GPU architecture with 64-bit operating capability, integrated advanced multi-function video and image processing, and NVIDIA Deep Learning Accelerators.
    • Hand-Size Edge AI Device: Compact size at 63mm x 95mm x 66.7mm, featuring an NVIDIA Jetson Orin NX 16GB module, Mini J401 carrier board, fan and enclosure. Support desktop and wall mounting.
    • Expandable with Rich I/Os: Includes up to 8x USB, DP 1.4, 1x RJ45 for GbE, M.2 Key E, M.2 Key M, dual channel CAN, and GPIO.
    • Accelerate Solutions to Market: Pre-installed JetPack 6.0 on 128GB NVMe SSD, Linux OS BSP, supporting Jetson software and leading AI frameworks.
    • Scale to deploy: support OTA, remote management services powered by Allxon and Balena.
    • Flexible Customization: inlcudes changing accessories modules, logo, and hardware interfaces modification based on reComputer Mini J4012 original design.

    Specification

    Jetson Orin System on Module

    AI Performance

    reComputer Mini J4012 with Extension - Orin NX 16GB, 100 TOPS

    reComputer Mini J3011 with Extension - Orin Nano 8GB – 40 TOPS

    GPU

    1024-core NVIDIA Ampere architecture GPU with 32 Tensor Cores

    CPU

    8-core Arm® Cortex®-A78AE v8.2 64-bit CPU (Orin NX 16GB)

    6-core Arm® Cortex®-A78AE (Orin Nano 8GB)

    Memory

    16GB 128-bit LPDDR5 (Orin NX 16GB)

    8GB 128-bit LPDDR5 (Orin NX 8GB)

    Video Encode

    1x 8K30 (H.265) | 2x 4K60 (H.265) | 4x 4K30 (H.265) | 9x 1080p60 (H.265) | 18x 1080p30 (H.265)

    1080p30 supported by 1-2 CPU cores

    Video Decode

    1x 8K30 (H.265)

    2x 4K60 (H.265)

    4x 4K30 (H.265)

    9x 1080p60 (H.265)

    18x 1080p30 (H.265)

    1x 4K60 (H.265)

    2x 4K30 (H.265)

    5x 1080p60 (H.265)

    11x 1080p30 (H.265)

    DL Accelerator

    2x NVDLA v2

    /

    Carrier Board

    Storage

    1x M.2 Key M PCIe (M.2 NVMe 2242 SSD 128G included)

    Networking

    M.2 KEY E

    1x M.2 Key E for WiFi/Bluetooth module

    I/O

    USB

    2x USB 3.2 Type-A (10Gbps);

    1x USB 2.0 Micro-B (Device Mode);

    1x USB 3.2 Type-C (Host Mode);

    1x USB 2.0 JST-5pin (Host Mode);

    UART

    1x UART

    1x Debug Uart

    Display

    1x DP 1.4 (included in Type-C conenctor)

    Fan

    1x 4 pin Fan Connector (5V PWM)

    Button

    1x Reset Button; 1x Recovery Button

    Extension Port

    2x 60 pin High Speed Connector (For extension board)

    1x 10 pin Power Connector (For extension board)

    RTC

    1x RTC 2-pin

    Power

    1 x XT30 Connector (12-54V DC)

    Extension Board

    Networking

    Ethernet

    1x RJ-45 Gigabit Ethernet (10/100/1000M)

    I/O

    USB

    4 x USB 3.0 Type-A (5 Gbps)

    CAN

    1 x CAN JST 4pin (5V)

    1 x CAN (XT30 2+2)

    FAN

    1x 4 pin Fan Connector (5V PWM)

    I2C

    2 x I2C JST 4pin (3.3V)

    SPI

    1 x SPI JST 6pin (3.3V)

    Power

    2 x XT30(2+2) Connector (12-54V DC)

    Mechanical

    Dimensions (W x D x H)

    63mm x 95mm x 42mm (Without Extension)

    63mm x 95mm x 66.7mm (With Extension)

    Weight

    345g (Without Extension)

    462g (With Extension)

    Installation

    Desk, Wall-mounting

    Operating Temperature

    -10℃~50℃

    Warranty

    1 Year

    Hardware Overview

    ● Desktop, wall Mount, expandable, or fit in anywhere


    Application

    ● Robotic Control

    • Capable of Bringing Generative AI to the Edge

    Now you can build AI agents capable of processing large amounts of live or archived videos and images with Vision-Language Models (VLM) such as LLaVA, this new AI agents help nearly every industry summarize, search, and extract actionable insights from video using natural language.

    • Build Multi-streams AI Video Analytics

    For building video analytics, Jetson Orin NX incorporates the NVIDIA Multi-Standard Video Decoder. This video decoder accelerates video decode, supporting low resolution mobile content, Standard Definition (SD), High Definition (HD) and UltraHD (8K, 4K, etc.) reComputer J4012 can take 18x1080p30 streams. See our tested YOLOv8 performance using NVIDIA Deepstream of single model and multi model on multi streams.

    • Fastest Way to Deploy Generative AI and Computer Vision Models

    We have jetson-example prepared for you! It offers one-line deploy projects edge AI applications of generative AI including Ollama, Llama3; computer vision including YOLOv8; and others. We have configured all environment for you to provides single command deployment of projects.


    Read more

    Recently viewed products

    Login

    Forgot your password?

    Don't have an account yet?
    Create account