Deep Learning Module

   SBC - 6841 processor compact system operation module (SOM), which is third generation TPU chip BM1684 independently developed by SOPHGO, IT has the INT8 computing power of 17.6TOPS and can process more than 16 channels of HD video at the same time. It has rich IO interfaces, which are easy to integrate with various edge or embedded devices. It is applied to a variety of visual computing deep learning scenarios, such as intelligent security, park, retailing, power, industrial robot, UAV, etc. The product is highly compatible with NX module and convenient to migrate algorithm. At the same time, it supports SBC - 6841 developer kit.


Specification and Characteristic

Product Model
Application Scenarios

Deep Learning BOX, intelligent gateway, micro server, intelligent server

Deep Learning Processor
Deep Learning Performance
Supports FP32/INT8, capable of simultaneously processing 16 channels of high-definition video
Master Processor
8-core ARM A53, basic frequency up to 2.3GHz
8+4GB 128-bit LPDDR4X
Video Decoding Capability
1080P@960fps, support H264 & H265
Video Encoding Capability
Picture Codec Capability
1080P 480 image/sec
Network Interface
1x Gigabit Ethernet
USB Interface
3 * USB2.0, 1 * USB3.1
Other Interface
PCIE x4 (1x), PCIE x1(1x), I2C x3, I2S x1, UART x3, SDIO x1
Input Voltage
DC5V ±5%
70mm x 45mm
Other Parameters

260-PIN SO-DIMM, 1 * PCIE x4, 1 * PCIE x1, 3 * USB2.0, 1 * USB3.1, 3 * I2C, 1 * I2S, 3 * UART, 1 * SDIO

Operating Temperature
Storage Temperature
Operating Humidity
10~90%, no condensation

Partner Introduction

At the request of partners, partner information is temporarily unavailable.

If you have any needs, please return to the " TEAM Ecological Products " page, click " Submit Hardware Request " to fill in with product model and submit.