Toggle Nav

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


Jetson SUB Mini PC-Blue is based on Jetson Xavier NX module, which delivers up to 21 TOPS, making it ideal for high-performance compute and AI in embedded and edge systems. Jetson Sub mini PC blue is pre-installed Wifi module and antenna. The carrier board comes with rich peripherals including Gigabit Ethernet port, 4 USB 3.1 Type-A ports, HDMI and DP. 

Check out more NVIDIA Jetson-powered edge devices comparison!

reComputer J2021 built with Jetson Xavier NX




1. Please check out the latest reComputer Jetson-20 built with Xavier NX 8GB/16GB.

2Jetson SUB Mini PC with Xavier NX 8GB is available shipped in May.

For more NVIDIA product purchase solutions, click here.


  • 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/nvidia
2. sudo./ssd
to make sure the roof expands to take the unallocated 110GB space.


  • Compact design for a mini PC with an overall dimension of 130mm*120mm*50mm
  • Powered by the6-core NVIDIA Carmel ARM®v8.2 64-bit CPU 6MB L2 + 4MB L3
  • 384-core NVIDIA Volta™ GPU with 48 Tensor Cores provides 21 TOPS AI performance
  • Rich peripherals including Gigabit Ethernet port, 4 USB 3.1 Type-A ports, HDMI port and DP port
  • Pre-installed Wifi module and antenna
  • Pre-installed 128GB (M.2 key M) SSD
  • Mounting design
  • Easy to install, upgrade and maintain with ease of access to the internal components after opening the enclosure
  • Pre-installed NVIDIA official JetPack software, ready to use
  • Compatible with Nimbus: connect your ROS project to the cloud


Strong module - Jetson Xavier NX 

At 70 mm x 45 mm, Jetson Xavier NX packs the power of the NVIDIA Xavier SoC into a module the size of a Jetson Nano™. This compact module combines exceptional performance and power advantage with a rich set of IOs—from high-speed CSI and PCIe to low-speed I2Cs and GPIOs. Take advantage of the small form factor, sensor-rich interfaces, and big performance to bring new capability to all your embedded AI and edge systems.


Jetson Xavier NX delivers up to 21 TOPS, making it ideal for high-performance compute and AI in embedded and edge systems. You get the performance of 384 NVIDIA CUDA® Cores, 48 Tensor Cores, 6 Carmel ARM CPUs, and two NVIDIA Deep Learning Accelerators (NVDLA) engines. Combined with over 59.7GB/s of memory bandwidth, video encoded and decoded, these features make Jetson Xavier NX the platform of choice to run multiple modern neural networks in parallel and process high-resolution data from multiple sensors simultaneously.


Jetson Xavier NX supports multiple power modes, including low-power modes for battery-operated systems, and delivers up to 14 TOPs for AI applications in as little as 10 W. This leaves more of your power budget for sensors and peripherals, while still letting you use the entire NVIDIA software stack. You now have the performance to run all modern AI networks and frameworks with accelerated libraries for deep learning, computer vision, computer graphics, multimedia, and more.

Powerful carrier board and heatsink

The NVIDIA® Jetson Xavier NX™ module has assembled with a carrier board and cooling fan and they together called a ‘Kit’. It brings supercomputer performance to the edge. It includes a Jetson Xavier NX module for developing multi-modal AI applications with the NVIDIA software stack in as little as 10 W. You can also now take advantage of cloud-native support to more easily develop and deploy AI software to edge devices.

The kit is supported by the entire NVIDIA software stack, including accelerated SDKs and the latest NVIDIA tools for application development and optimization. Meanwhile, we install a Wifi module (M.2 KEY E), 128GB SSD(M.2 M NVME) and two antennas. Users could just power the product, log in and use it directly.

Compatible enclosure

With an overall dimension of 130mm*120mm*50mm, it is only around 1/10 of the size of an ordinary computer case which makes it possible to be placed on a table, on a shelf, on any surface you want it to be. The back screw holes allow you to hang the product on the back of your Computer Screen. The neat structure of our mini PC kit also makes it simple to access the SSD and PCIe slots which allow for easy installation, upgrade and maintenance.


  • 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.
  • Check the link for more case detail.

  • It is also compatible with all popular SBCs. we have designed and left screw holes for the installation of the most popular SBCs including  ODYSSEY - X86 boardRaspberry PiBeagleBone and Jetson Nano. 


Jetson SUB Mini PC-Blue Jetson SUB Mini PC-Black Jetson SUB Mini PC-Silver Jetson EX1 Mini PC-Ubuntu
AI Performance 21 TOPs(INT8)
OS JetPack 4.6 Ubuntu 18.04
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 256GB SATA 128GB M.2 NVME   SSD 256GB M.2 NVME   SSD
Wifi Pre-installed M.2 E Wifi Pre-installed USB 2.0 Wifi Pre-installed M.2 E Wifi  \
Power 19V DC 19V DC 19V DC 12V DC
Display 1* HDMI / 1* DP 1* HDMI / 1* DP 1* HDMI / 1* DP 1* HDMI / 1* DP
1* OLED screen
USB 4* USB3.0(USB 2.0  Integrated), 4*USB3.0(USB 2.0  Integrated), 4*USB3.0(USB 2.0  Integrated), 1*USB3.0(USB 2.0  Integrated)
1*Micro USB 1*USB Type C 1*Micro USB 1*Micro USB,
Network 1* Gigabit Lan 2* Gigabit Lan*2 1* Gigabit Lan 2* Gigabit Lan
Dimension 130mm x120mm x 50mm 205mm x 130mm x 65mm 130mm x90mm x60mm 134mm x135mm x46mm
Key feature Blue Aluminum Case;  Whole Black Aluminium Frame; Whole Silver Aluminium Frame; Whole Black Aluminium Frame;
Removable  transparent Cover; Big passive  dissipation ; Portable Oval Size Narrow space fit,
Mounting hole design OLED screen Multiple software 
drivers installed
Reference application Indoor AIoT, Home development, etc. Industry IoT, 
Harsh environment applications, etc.
Smart Office, Smart Home, Education, etc. Industry control, Lab,  etc.

Module Technical Specifications
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)
12 lanes (3x4 or 6x2) MIPI CSI-2
D-PHY 1.2 (up to 30 Gbps)
Video Encode 2x 4K60 | 4x 4K30 | 10x 1080p60 | 22x 1080p30 (H.265)
2x 4K60 | 4x 4K30 | 10x 1080p60 | 20x 1080p30 (H.264)
Video Decode 2x 8K30 | 6x 4K60 | 12x 4K30 | 22x 1080p60 | 44x 1080p30 (H.265)
2x 4K60 | 6x 4K30 | 10x 1080p60 | 22x 1080p30 (H.264)
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
260-pin SO-DIMM connector

Carrier board Connector Description

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)


Jetson Xavier NX is perfect for high-performance AI systems like commercial robots, medical instruments, smart cameras, high-resolution sensors, automated optical inspection, smart factories, and other AIoT embedded systems.

Jetson Xavier NX now features cloud-native support that lets developers build and deploy high-quality, software-defined features on embedded and edge devices. Pre-trained AI models from NVIDIA NGC and the TAO Toolkit give you a faster path to trained and optimized AI networks, while containerized deployment to Jetson devices allows flexible and seamless updates. Jetson Xavier NX accelerates the NVIDIA software stack with more than 10X the performance of its widely adopted predecessor, Jetson TX2.

You can build fast AI projects with NVIDIA pre-trained models specially built for various industry examples, and accelerate the process model from the PoC to production. It can be easily used in common computer vision examples to collect statistics and statistics in dense artificial intelligence areas statistics. For example, detecting personnel, detecting and diagnosing vehicles, detecting and identifying license plates at toll gates, parking management, patient movement monitoring in medical and health institutions, etc. Yes, you can use it to monitor the driver's fatigue driving state like below.

Seeed is glad to partner with Cogniteam, aiming at delivering the easiest ever robot development process, from prototyping to production, including configuration, testing, deployment, and operations management. Try Nimbus with Seeed’s Jetson Platform carrier boards and Jetson Sub kit, attach sensors such as RPLidar and cameras to build your create your robotic application from scratch. You can also seamlessly connect your existing ROS projects to Nimbus. Based on the open-source Robot Operating System (ROS), Nimbus is truly a ‘plug and play’ solution.

Part List

1 x Acrylic Cover

1 x Aluminium Frame 

1 x Jetson Xavier NX module 

1 x Heatsink 

1 x Carrier board 

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

2 x Antennas 

Advantages Over the Original Version

Jetson Xavier NX Developer Kit

Jetson SUB Mini PC

AI Performance





NVIDIA Volta architecture with 384 NVIDIA CUDA® cores and 48 Tensor cores

NVIDIA Volta architecture with 384 NVIDIA CUDA® cores and 48 Tensor cores


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

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


8 GB 128-bit LPDDR4x @ 51.2GB/s

8 GB 128-bit LPDDR4x @ 59.7GB/s



2* HDMI / 2* HDMI+1* OLED screen



JetPack4.6 / Ubuntu 18.04


103 x 90.5 x 31(mm)

130 x 120 x 50(mm)/

205 x 130 x 65(mm)/

130 x 90 x 60(mm)/

134 x 135 x 46(mm)

Video Encode

2x 4K 30

6x 1080p 60

14x 1080p 30 (H.265/H.264)

2x 4K 60

4x 4K 30

10x 1080p 60

22x 1080p30 (H.265/H.264)

Video Decoder

2x 4K 60

4x 4K 30

12x 1080p 60

32x 1080p 30 (H.265)

2x 8K 30

6x 4K 60

12x 4K 30

22x 1080p 60

44x 1080p 30 (H.265)

2x 4K 30

6x 1080p 60

16x 1080p 30 (H.264)

2x 4K 60

6x 4K 30

10x 1080p 60

22x 1080p 30 (H.264)

M.2 Interfaces


M.2 Key E 2230

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

M.2 Key M 2280

Pre-installed 128GB NVME SSD



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

Button Header


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



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



2 x Antenna


Only Board

Acrylic sheet and metal shell


In the current market, the price of components are fluctuating greatly, and the lead time of some products may take 8 - 12 weeks. To help you plan ahead, we recommended that customers with large quantity requirements get in touch with us in advance at [email protected].Inform us of your schedule and required quantity, and we will do our best to accommodate your request.


HSCODE 8471504090
USHSCODE 8471410150
EUHSCODE 8471800000
CE 1
EU DoC 1
RoHS 1
UK DoC 1



Seeed is glad to partner with Cogniteam, aiming at delivering the easiest ever robot development process, from prototyping to production, including configuration, testing, deployment, and operations management.
Explore the interfaces, AI performances, and all differences among Seeed's edge AI devices and carrier boards for Jetson, as well as NVIDIA Official Dev Kts.
MaskCam is a prototype reference design for a Jetson Nano-based smart camera system that measures crowd face mask usage in real-time, with all AI computation performed at the edge. MaskCam detects and tracks people in its field of view and determines whether they are wearing a mask via an object detection, tracking, and voting algorithm.
Zenus leverages the power of Artificial Intelligence to create incredible products while driving the ethical use of facial analysis. Seeed supports the Zenus AI camera with Seeed's high-performance, interface-rich NVIDIA Jetson Nano/Xavier NX/TX2 NX compatible carrier board.
You can securely manage NVIDIA® JetPack 4.6 onward versions with Cyber Security at the Edge protecting all networks and hardware. Here are some operations about installing, getting code, adding devices etc.
Seeed is glad to partner with Allxon to deliver a secure remote management solution for Jetson Platform. At Seeed, you will find everything you want to work with NVIDIA Jetson Platform – official NVIDIA Jetson Dev Kits, Seeed-designed carrier boards, and kits, as well as third-party boards and accessories.



Write Your Own Review
Only registered users can write reviews. Please Sign in or create an account
  1. Product Quality
    from product detail summary
    Perfect platform for robotics, highly recommended.
  2. Product Quality
    from product detail summary
    Perfect platform for robotics, highly recommended.
  3. Product Quality
    from order view
    This is a great idea and about 90% "there" - the clear case lid sits directly on the SOC fan blocking the air - and the cables can be tricky to insert in to the carrier board. Neither are a deterrent, but definitely something to be improved.
  4. Product Quality
    from product detail summary
    This user did not leave any comments.


4 Item(s)

Show per page