ArmSoM
Embedded Linux Boards
Machine Learning

RK3588 AI Module7

A low-power AI module compatible with the Nvidia Jetson Nano ecosystem

This project is launching soon.

Coming Soon
0
updates
You'll be notified about news and stock updates for this project.

RK3588 AI Module7, powered by the Rockchip RK3588, offers a robust 64-bit octa-core processor with a maximum clock speed of 2.4 GHz, a 6 TOPS NPU, and supports up to 32 GB of memory. It is compatible with Nvidia’s Jetson Nano interface with upgraded and improved PCIe connectivity. Due to this module’s versatility, it caters to applications such as edge computing, cloud servers, AI, VR/AR, blockchain, and smart NVR security systems, not to mention general-purpose computing.

AIM-IO is a compact IO board compatible with current Jetson Nano core modules. With RK3588 AI Module7 installed, it becomes a mini AI computer designed for makers, learners, and developers capable of quickly implementing machine learning technology in various smart devices.

Unlock NPU Performance

With its Jetson Nano-style edge connector, RK3588 AI Module7 neatly fits into an existing, broad ecosystem of carriers and other compatible accessories. And with its powerful NPU, it’s excellent for intensive ML/AI tasks. Other use cases for ArmSoM RK3588 AI Module7 include:

Comparisons

SpecificationsArmSoM RK3588 AI Module7 (Rockchip)Jetson Nano (NVIDIA)
CPU CoresQuad-core ARM Cortex-A76 + Quad-core ARM Cortex-A55 Quad-core ARM Cortex-A57 processor
GPU CoresARM Mali-G610 MP4128-core Maxwell GPU
Memory8 GB/32 GB LPDDR4x, 2112 MHz 4 GB LPDDR4, 1600 MHz
StoragemicroSD card, 32GB eMMC 5.1 flash storagemicroSD card, 16GB eMMC 5.1 flash storage
Video Encoding8K@30 fps H.265 / H.2641x 4K@30 (HEVC), 2x 1080p@60 (HEVC), 4x 1080p@30 (HEVC)
Video Decoding8K@60 fps H.265/VP9/AVS2, 8K@30 H.264 AVC/MVC, 4K@60 fps AV1, 1080P@60 MPEG-2/-1/VC-1/VP81x 4K@60 (HEVC), 2x 4K@30 (HEVC), 4x 1080p@60 (HEVC), 8x 1080p@30 (HEVC)
USB Ports1x USB 3.0, 3x USB 2.01x USB 3.0, 3x USB 2.0
Ethernet1x 10/100/1000 BASE-T1x 10/100/1000 BASE-T
CSI Interfaces12 channels (4x2) MIPI CSI-2 D-PHY1.1 (18 Gbps)12 channels (3x4 or 4x2) MIPI CSI-2 D-PHY 1.1 (18 Gbps)
I/O3 UARTs, 2 SPIs, 2 I2S, 4 I2Cs, multiple GPIOs3 UARTs, 2 SPIs, 2 I2S, 4 I2Cs, multiple GPIOs
PCIe1x 1/2/4 lane PCIe 3.0 & 1x 1 lane PCIe 2.0 1x 1/2/4 lane PCIe 2.0
HDMI Output1x HDMI 2.1 / 1x eDP 1.4 1x HDMI 2.0
DP Interface1x DP 1.4a 1x DP 1.2
eDP/DP Interface1x eDP 1.41x eDP 1.4 / 1x DP
DSI Interface1x DSI (1x2) 2 sync1x DSI (1x2) 2 sync
OS SupportDebian, Ubuntu, Armbian NVIDIA JetPack software suite

Performance

Geekbench source data: 1, 2, 3

Features & Specifications

AIM-IO Carrier Board

The AIM-IO Board is a companion board for AIM modules designed to assist developers using AIM modules in completing system and embedded board development. Compared to the Jetson Nano Developer Kit (B01), the AIM-IO Board is the same size but has a broader array of expansion options.

Open Source

The firmware source and board schematics will be made available during the crowdfunding campaign.

Interested in This Project?

You can sign up at the top of this page to be notified when the campaign launches and to receive other updates. We provide useful information only, and you can unsubscribe at any time.

In the Press

Hackster News

"The company is positioning the module, which comes with a choice of 8GB or 32GB of LPDDR4x memory, as a upgrade over NVIDIA's entry-level Jetson Nano module — offering a higher-performance CPU, dedicated NPU, and more memory"

Linux Gizmos

"[The ArmSoM RK3588 AI Module7 is] an open-source device... designed for a diverse array of applications, including computer cluster nodes, on-premise servers, and projects involving 3D graphics and AI."

It's FOSS News

"An interesting new AI module with a board aimed to offer compatibility with the Jetson Nano interface."

About the Team

ArmSoM

 · 

We are an open-source hardware and software company founded in 2021 by a passionate team of young developers in Shenzhen. We are driven by a belief in the power of open innovation and are committed to providing the open-source community with exceptional hardware, robust firmware, and comprehensive documentation. Upholding open-source values, we also deliver customizable ODM solutions to businesses worldwide.

Jackson
Yla
Leon
Jose
Park
Yangyu
Yijin
Xikan
Daisy

See Also

Subscribe to the Crowd Supply newsletter, highlighting the latest creators and projects