Jetson SUB Mini PC-Blue with Jetson Xavier NX module, Aluminium case with cooling fan, 128GB SSD, WiFi, Antennas and pre-installed JetPack System
Edge

Jetson SUB Mini PC-Blue with Jetson Xavier NX module, Aluminium case with cooling fan, 128GB SSD, WiFi, Antennas and pre-installed JetPack System

Seeed Studio

Overview

Jetson SUB Mini PC-Blue is an edge AI computer from Seeed Studio built on the NVIDIA Jetson Xavier NX module. Its GPU is 384-core NVIDIA Volta GPU. It carries 8 GB 128-bit LPDDR4x 59.7GB/s. Seeed publishes a fixed price for this configuration.

Key Features

  • Built on the NVIDIA JETSON XAVIER NX module
  • GPU: 384-core NVIDIA Volta GPU
  • CPU: 6-core 64-bit CPU, NVIDIA Carmel ARMv8.2
  • Memory: 8 GB 128-bit LPDDR4x 59.7GB/s
  • Storage: 16 GB eMMC 5.1
  • Networking: 10/100/1000 BASE-T Ethernet

Ideal For

teams deploying Jetson Xavier NX-class inference at the edge in a finished, cased unit

Module

NVIDIA JETSON XAVIER NX

AI Performance

21 TOPs(INT8)

OS

JetPack 4.6

CPU

6-core 64-bit CPU, NVIDIA Carmel ARMv8.2

GPU

384-core NVIDIA Volta GPU

Memory

8 GB 128-bit LPDDR4x 59.7GB/s

Module Storage

16 GB eMMC 5.1

Carrier Board Storage

128GB M.2 NVME   SSD

Wifi

Pre-installed M.2 E Wifi

Power

19V DC

Display

1* HDMI / 1* DP

USB

4* USB3.0(USB 2.0  Integrated),

1*Micro USB

1*USB Type C

Network

1* Gigabit Lan

Dimension

130mm x120mm x 50mm

Key feature

Blue Aluminum Case;

Removable  transparent Cover;

Big passive  dissipation ;

Mounting hole design

OLED screen

Reference application

Indoor AIoT, Home development, etc.

AI Performance

21 TOPS

GPU

384-core NVIDIA Volta™ GPU with 48 Tensor Cores

CPU

6-core NVIDIA Carmel ARM®v8.2 64-bit CPU, 6MB L2 + 4MB L3

Memory

8 GB 128-bit LPDDR4x, 59.7GB/s

Storage

16 GB eMMC 5.1

Power

10 W | 15 W | 20W

PCIe

1 x1 (PCIe Gen3) + 1 x4 (PCIe Gen4), total 144 GT/s*

CSI Camera

Up to 6 cameras (24 via virtual channels)

Video Encode

2x 4K60 | 4x 4K30 | 10x 1080p60 | 22x 1080p30 (H.265)

Video Decode

2x 8K30 | 6x 4K60 | 12x 4K30 | 22x 1080p60 | 44x 1080p30 (H.265)

Display

2 multi-mode DP 1.4/eDP 1.4/HDMI 2.0

DL Accelerator

2x NVDLA Engines

Vision Accelerator

7-Way VLIW Vision Processor

Networking

10/100/1000 BASE-T Ethernet

Mechanical

69.6 mm x 45 mm

Carrier board Connector

Description

HDMI Port

1* HDMI / 1* DP

USB 3.0 Type A

4*USB 3.0 Type A Connector

NVIDIA Gigabit Ethernet

1*RJ45 Gigabit Ethernet Connector (10/100/1000)

DC Power

1*DC Input Power TE Connector

FAN Connect

1*Picoblade Header

M.2 KEY E 2230

Pre-installed Wifi module (802.11ac, Dual Band, 80MHZ, MU-MIMO & Bluetooth 4.2)

CSI Camera Connect

2*CSI Camera (15 pos, 1mm pitch, MIPI CSI-2 )

Multifunctional port

2.0 Pitch 40 PIN

M.2 KEY M 2280

Pre-installed 128GB NVME SSD

NVIDIA Jetson Nano/NX/TX2 NX connector

1*Jetson SODIMM connector, 260-pin

CAN

1*CAN Bus Header (1x4, 2.54mm pitch, RA)

Button Header

1*Button Header (1x12, 2.54mm pitch, RA)

USB Micro Type B

1*USB Micro B, RA Female

RTC

1*RTC Back-up Coin Cell Socket (CR1225)

Feature

Compact design for a mini PC with an overall dimension of 130mm*120mm*50mm

Feature

Powered by the6-core NVIDIA Carmel ARM®v8.2 64-bit CPU 6MB L2 + 4MB L3

Feature

384-core NVIDIA Volta™ GPU with 48 Tensor Cores provides 21 TOPS AI performance

Feature

Rich peripherals including Gigabit Ethernet port, 4 USB 3.1 Type-A ports, HDMI port and DP port

Feature

Pre-installed Wifi module and antenna

Feature

Pre-installed 128GB (M.2 key M) SSD

Feature

Mounting design

Feature

Easy to install, upgrade and maintain with ease of access to the internal components after opening the enclosure

Feature

Pre-installed NVIDIA official JetPack software, ready to use!

Compatible with Nimbus

connect your ROS project to the cloud

Industry 4.0

helmet detection, hard hat detection, and custom PPE detection visual anomaly detection using NVIDIA Deepstream IoT

Feature

helmet detection, hard hat detection, and custom PPE detection

Feature

visual anomaly detection using NVIDIA Deepstream IoT

Retail

sentiment analysis(webinar: learn your customer with AI by Zenus smart camera), retail store items detection

sentiment analysis(webinar

learn your customer with AI by Zenus smart camera),

Feature

retail store items detection

Robotics

under-ice sensing ROV warehouse towing robot

Feature

under-ice sensing ROV

Feature

warehouse towing robot

Feature

Traffic management

Edge AI into the Wild

Wildfire detection

Agriculture

weeding machine, Tractors, Livestock detection

Healthcare

medical imaging analysis

Feature

The top acrylic cover is removable. If you want to add a HAT or Cape on your SBC inside the case, there is no need to re-screw the whole case because the top acrylic layer is designed to be removed easily.

Feature

1 x Acrylic Cover

Feature

1 x Aluminium Frame

Feature

1 x Jetson Xavier NX module

Feature

1 x Heatsink

Feature

1 x Carrier board

Feature

1 x 19V/4.74A (MAX 90W) Power Adapter (Power cable not included)

Feature

2 x Antennas

Note The power cord and 3V RTC battery (CR1220) are not included, please choose a suitable form according to your country. Pre-installed JetPack™ system, the login password is 'nvidia'. If you want to reflash the system, you need to enter recovery mode, check wiki for more details. Before using it, you need to open a terminal and execute the following

1. cd /home/nvidia2. sudo./ssd extern.shto make sure the roof expands to take the unallocated 110GB space.

Feature

The power cord and 3V RTC battery (CR1220) are not included, please choose a suitable form according to your country.

Feature

Pre-installed JetPack™ system, the login password is 'nvidia'. If you want to reflash the system, you need to enter recovery mode, check wiki for more details.

Feature

Before using it, you need to open a terminal and execute the following:

$279.00

Prices may vary. Verify on vendor site.

Quick Specs

Module
NVIDIA JETSON XAVIER NX
AI Performance
21 TOPS
OS
JetPack 4.6
CPU
6-core NVIDIA Carmel ARM®v8.2 64-bit CPU, 6MB L2 + 4MB L3
GPU
384-core NVIDIA Volta™ GPU with 48 Tensor Cores
Memory
8 GB 128-bit LPDDR4x, 59.7GB/s

Tags

edge-inferencecomputer-visionroboticsmulti-gpusmall-modelmedium-modellarge-modelhigh-vram