AIO-3588JD4 AI Motherboard RK3588

Regular price $229.00 USD
Regular price Sale price $229.00 USD
Shipping calculated at checkout.

⭐️Get 5% Off (First Order) - Code: TCHIP5

Storage: 4G RAM+32G ROM
Spec: SoM with Carrier Board (AIO-3588JD4)
  • American Express
  • Google Pay
  • Mastercard
  • PayPal
  • Shop Pay
  • Union Pay
  • Visa
Brand: Firefly
Availability: 3 in stock
Regular price $229.00 USD
Regular price Sale price $229.00 USD

The AIO-3588JD4 motherboard is a powerful embedded computing board designed for AI and edge computing applications. With 6 TOPS of NPU computing power, it delivers efficient AI acceleration for machine learning and deep learning tasks. This board enables private deployment of large AI models, ensuring secure and flexible on-device intelligence. It supports multiple deep learning frameworks, making it easy for developers to deploy and optimize AI algorithms. Additionally, it features 8K ultra-HD video decoding, ideal for high-resolution video processing, smart vision systems, and edge AI solutions.

Perfect for industrial automation, smart cities, AIoT, and robotics, the AIO-3588JD4 offers high performance, scalability, and reliability for next-generation AI applications.

Feature

  • Octa-core AI Processor RK3588: The AIO-3588JD4 is equipped with Rockchip's flagship processor, the RK3588, an octa-core 64-bit CPU that delivers 6 TOPS of computing power, enhancing performance for AI application scenarios.
  • Custom Private Deployment of AI Models: Supports private deployment of rich parameter models based on the Transformer framework, including Gemma-2B, ChatGLM3-6B, Qwen1.5-1.8B, Phi-3-3.8B and other rich language models.
  • Decoding of 8K Ultra-High Definition Video: It supports 8K HD video decoding, presenting clearer images and richer details, and adopts a 2D hardware engine to significantly improve display performance.
  • Industrial-Grade Stability: Supports external watchdog timer and industrial-grade stability. Compatible with multiple operating systems, it is suitable for ARM PCs, edge computing, cloud servers, smart NVRs, and other fields.

Hardware Overview

Ai performance
  • Support the privatization deployment of ultra-large-scale parametric models under the Transformer architecture, such as Gemma-2B, ChatGLM3-6B, Qwen-1.8B, Phi-3-3.8B and other large language models
  • It supports traditional network architectures such as CNN, RNN, and LSTM, and supports the import and export of RKNN models; Support a variety of deep learning frameworks, including TensorFlow, TensorFlow Lite, PyTorch, Caffe, ONNX and Darknet. It also supports the development of custom operators
  • Support Docker container management technology
Soc

Rockchip RK3588

Cpu

Octa-core 64-bit processor (4×Cortex-A76+4×Cortex-A55) , main frequency up to 2.4GHz

Gpu

ARM Mali-G610 MP4 quad-core GPU, support OpenGL ES3.2/OpenCL 2.2/Vulkan1.1, 450 GFLOPS

Npu

The computing power is up to 6TOPS(INT8), support INT4/INT8/INT16 mixed operations

Ram

LPDDR4/LPDDR4x (4GB/8GB/16GB optional, up to 32GB)

Storage

eMMC (32GB/64GB/128GB/256GB optional)

Storage expansion

1 × TF Card, 1 × M.2 (Expandable SATA 3.0/PCIe NVMe SSD, supports 2242/2260/2280 specifications)

Power

DC 12V (5.5mm × 2.1mm, support 9V~24V wide voltage input)

Power consumption

Max: 14.4W(12V/1200mA), Normal: 4.8W(12V/400mA), Min: 0.636W(12V/53mA)

Video output

1 × HDMI2.1(8K@60fps or 4K@120fps)

Video input

2 × MIPI CSI DPHY (1×4lanes or 2×2lanes, 30Pin-0.5mm), Line in (Led by double row headers)

Audio

1 × 3.5mm Audio jack (Support MIC recording, American Standard CTIA)

Os

Android, Linux

Dimension

122.89mm × 85.04mm × 22.46mm

Weight

≈120g

Environment
  • Operating Temperature: -20℃~60℃,
  • Storage Temperature: -20℃~70℃,
  • Storage Humidity: 10%~90%RH(non-condensing)
Watchdog

Independent watchdog

Usb

2 × USB3.0 (Max: 1A; UP: USB3.0(1), reused with 5G; DOWN: USB3.0(2))

Other
  • 1 × Type-C (OTG), 1 × FAN (4Pin-1.25mm), 1 × SIM Card
  • 1 × Double-row pin headers (2×10-20PIN-2.0mm): USB2.0, SPI, 2×I2C, Line in, Line out, GPIO
  • 1 × Phoenix connector (2×4Pin, 3.5mm pitch): 1 × RS485, 1 × RS232, 1 × CAN 2.0
Sdk software and firmware files Click Here

More details about Shipping Policy: Click Here

Our cooperating carriers: FedEx, DHL, UPS, SF Express

Delivery Area And Cost

Country/Region 0.0001-2kg 2.0001-3kg 3.0001-4kg 4.0001-5kg 5.0001-6kg 6.0001-7kg 7.0001-8kg 8.0001-9kg 9.0001-10kg
Japan, Taiwan, Hong Kong, Macau $15 $20 $25 $30 $35 $40 $45 $50 $55
Indonesia, Philippines $25 $30 $40 $50 $60 $70 $80 $85 $95
South Korea $25 $35 $35 $45 $45 $55 $55 $65 $65
Finland, France, Germany, Greece, Ireland, Italy, Netherlands, Norway, Portugal, Spain, Sweden, Switzerland, United States, Australia, New Zealand, Austria, Belgium, Denmark $30 $45 $55 $65 $75 $85 $95 $105 $115
Canada, United Kingdom $40 $50 $60 $75 $85 $95 $105 $115 $130
Hungary, India, Israel, Laos, Myanmar, Poland, Saudi Arabia, Turkey, United Arab Emirates, Vietnam, Bangladesh, Qatar, Cyprus, Pakistan, Brunei, Sri Lanka, Jordan, Oman, Maldives, Bulgaria, Iceland, Slovakia, Lithuania, Romania, Albania, Armenia, Mexico, Nepal, Serbia, Cambodia, Croatia, Czech Republic, Slovenia, Kazakhstan $50 $65 $80 $95 $110 $125 $135 $150 $165
Singapore, Thailand, Malaysia $20 $25 $30 $35 $40 $45 $50 $55 $60

 

Shipping Time (for reference only, the actual situation shall prevail):

Area  Shipping time
Europe 3 - 7 business days
Asia, Oceania 3 - 7 business days
North America 3 - 7 business days
South America 5 - 10 business days

 

Please check which area your region/country is in.

Order preparation time: 3-7 business days (specific details need to refer to the order situation).