Octa-Core 32T High Computing Power AI Embedded Computer

Powered by SOPHON AI processor BM1684X, this computer can be configured with 16GB of RAM. With up to 32TOPS of INT8 computing power,
it provides mainstream programming frameworks and a complete, easy-to-use toolchain, featuring low cost of algorithm migration.
This computer can be applied to visual computing, edge computing, general computing service, intelligent transportation,
smart classroom, unmanned supermarket, and surveillance security, and more

New-gen Octa core AI processor BM1684X

This computer is powered by SOPHON AI processor BM1684X, which features octa-core ARM Cortex-A53, frequency of up to 2.3GHz and 12nm
lithography process. With up to 32Tops (INT8) computing power, or 16TFLOPS (FP16/BF16) computing power, or 2Tops (FP32) high-precision
computing power, it supports mainstream programming frameworks, and can be widely used
in artificial intelligence inference for cloud and edge applications

Powerful multi-channel video AI performance

The computer supports up to 32-channel 1080P H.264/H.265 video decoding. It is able to simultaneously process and analyze over 16-channel
HD video, making it ideal for various AI applications such as face detection and license plate recognition on video streaming

High throughput and energy efficiency ratio

Based on measured data using Batch4 INT8 quantization, EC-A1684XJD4 FD has higher throughput and energy efficiency ratio
than the mainstream intelligent computing module platform in the industry and offers superior performance

Strong network expansion capability

It supports dual 1000Mbps Ethernet, 2.4GHz/5GHz dual-band WiFi, 5G/4G LTE network expansion, enabling higher-rate communication

One-stop toolkit, convenient and efficient

The SOPHON SDK one-stop deep learning development toolkit provides a series of software tools, including the underlying driver environment,
compiler, and inference deployment tool. It supports mainstream frameworks: Caffe/TF/PyTorch/Mxnet/Paddle, mainstream network
model and custom operator development, Docker containerization, and rapid deployment of algorithm applications.

Complete software and hardware

With complete software and hardware, artificial intelligence inference for cloud and edge applications can be easily achieved. All of them accelerate
development of edge applications, such as face recognition, video structuring, abnormal alarm, equipment inspection, and situation prediction, etc

A variety of interfaces

Featuring a variety of interfaces including HDMI, M.2 (SATA), USB3.0, USB2.0, RS485 and RS232,
the device can be directly applied to AI edge computing products

Fanless design and excellent heat dissipation

Equipped with an industrial-grade, all-metal enclosure, an aluminum alloy structure, and a fanless design, the device provides efficient heat
dissipation and stays completely silent. It enables stable operation and meets a wide range of industrial-grade application needs

A wide range of applications

The device can efficiently adapt to all AI algorithms in the market and integrate into edge computing boxes. It provides powerful AI performance
for a range of industries, including visual computing, edge computing, general computing service, artificial intelligence, intelligent construction
site, intelligent transportation, smart classroom, unmanned supermarket, security surveillance, and more

Computing server
Edge calculation
Traffic control
Self service market


Basic Specifications



High-performance octa-core ARM A53, 12nm lithography process, frequency up to 2.3GHz


Built-in tensor computing module TPU, computing power up to:

32TOPS (INT8), 16TFLOPS (FP16/BF16), 2TFLOPS (FP32)

Support mainstream programming frameworks:

TensorFlow / Caffe / PyTorch / Paddle / ONNX / MXNet / Tengine / DarkNet


32-channel H.265/H.264 1080p@25fps video decoding

32-channel 1080P@25fps HD video processing (decoding + AI analysis)

Support 12-channel H.265/H.264 1080p@25fps video encoding




32GB/64GB/128GB eMMC, 128MB SPI Flash,

1*M.2 SATA3.0 (Inside the computer. Capable of 2242 SSD expansion), 1*TF card slot


2*1000Mbps Ethernet

Wireless Network

2.4GHz/5GHz dual-band WiFi, 802.11a/b/g/n/ac,

capable of 4G LTE expansion (Mini PCIe), 5G (M.2)

Video Output


Audio Output

1*HDMI audio output


2*USB3.0 (current limit: 1A), 2*USB2.0 (current limit: 500mA)


DC 12V/5A (DC5.5×2.5mm)

Other Interfaces





182.5mm * 150.0mm * 66.5mm


≈ 1.8kg


Operating Temperature: -20℃~60℃

Storage Temperature: -20℃~70℃

Operating Humidity: 10%~90% (non-condensing)