Skip to content
Permalink
Branch: master
Find file Copy path
Find file Copy path
Fetching contributors…
Cannot retrieve contributors at this time
98 lines (93 sloc) 5.44 KB
title layout shortname permalink description keywords display_product product_short_desc product_specification product_sub_specification featured_product_order is_featured product_images tab_menu product_buy_links product_os product_more_info product archived
TB-96AIoT
product-display-page
tb-96aiot
/product/tb-96aiot/
The TB-96AIoT is a low-power, high-powered core board for the AIoT field. It is equipped with a powerful neural network processing unit (NPU) and is compatible with a variety of mainstream inference models such as caffe and tensor flow. Together with the bottom board CarrierBoard developed by Xiamen Beiqi Technology Co., Ltd., it can form a complete development board or evaluation board; the base board that can be customized according to the actual needs of the customer can directly form the industrial application board, which can meet the sweeping robot, drone, smart speaker. , automotive products, smart wear, security monitoring, AI computing modules and other areas of demand.
processing, power, Wi-Fi, Bluetooth connectivity, GPS, development, board, mid-tier, Qualcomm, APQ8016E, processor, low cost, Product, Development, Platform
true
The TB-96AIoT is a low-power, high-powered core board for the AIoT field.
se
module
2
true
96-TB-AIoT_Top.png
96-TB-AIoT_Bottom.png
96-TB-AIoT_Carrier_top1.png
96-TB-AIoT_Carrier_top2.png
tab_title tab_link active
TB-96AIoT
/product/tb-96aiot/
true
tab_title tab_link tab_position
Getting Started
/documentation/som/tb-96aiot/getting-started/
1
tab_title tab_link tab_position
Documentation
/documentation/som/tb-96aiot/
3
tab_title tab_link tab_position tab_align_right
Support
4
true
link-title link-url from type link-price link-price-currency
Coming Soon...
BeiqiCloud
board
TBC
USD
title link
All Downloads
/documentation/som/tb-96aiot/downloads/
true
false

The TB-96AIoT is a low-power, high-powered core board for the AIoT field. It is equipped with a powerful neural network processing unit (NPU) and is compatible with a variety of mainstream inference models such as caffe and tensor flow. Together with the bottom board CarrierBoard developed by Xiamen Beiqi Technology Co., Ltd., it can form a complete development board or evaluation board; the base board that can be customized according to the actual needs of the customer can directly form the industrial application board, which can meet the sweeping robot, drone, smart speaker. , automotive products, smart wear, security monitoring, AI computing modules and other areas of demand.

Features

  • CPU - Dual-core ARM Cortex-A53 CPU for ultra-low power consumption.
  • Built-in neural network processor NPU, super high AI computing power
  • Video codec
  • Rich extension interface for AIoT applications
  • High-speed on-board connector for more stability and reliability
  • Ultra-high integration, ultra-small size
  • Easy to develop
  • Rich open materials, 96Boards community

Additional Information

Component Description
SoC Rockchip RK1808(22nm FD-SOI)
CPU Dual Cortex-A35@1.6GHz
NPU Support 8bit/16bit operation, computing power up to 3.0TOPS / Support TensorFlow, Caffe model
VPU 1080p@60P H.264 Decoder,1080p@30P H.264 Encoder
RAM Optional configuration with the following options: 1GB LPDDR3 / 2GB LPDDR3 / 4GB LPDDR3
Storage Optional configuration with the following options: 16GB eMMC /32GB eMMC /64GB eMMC /128GB eMMC
Wifi/Bluetooth Built-in WiFi/BT module, reserved antenna holder, can be directly inserted into the antenna
Ethernet Port Built-in Gigabit Ethernet PHY chip, 10/100/1000Mbps adaptive
USB USB2.0 HOST ×1 - USB3.0 DRM ×1
Display One MIPI-DSI interface, up to 1920×1080@60fps display output
Audio Speakerx1 / Headphone×1 / Mic×1 / I2S×1
Expansion Interface PCIE×1 / I2C×3 / UART Debug×1 / SPI×2 / SD Card ×1 / PWM×1 / ADC×2
Power Source DC 5V
OS Support Linux (The supported Linux distribution is buildroot-2018.02-rc3 / The supported Linux kernel version is 4.4)
Size 50mm x 50 mm
{:.hidden_rows}
You can’t perform that action at this time.