Adopts Rockchip quad-core 64-bit processor RK3328, onboard AI neural network acceleration chip, with high computing capacity, ultra-high performance, powerful hardware decoding ability and rich extended interfaces, supports multiple operating system. It can be used as visual-based deep learning operation and AI algorithm acceleration, suitable for cluster servers, high-performance computing/storage, industrial computers, etc.

Specification

Specification
SoC	Rockchip RK3328
CPU	Quad-core ARM® Cortex-A53 64-bit processor, frequency up to 1.5GHz
GPU	ARM Mali-450 MP2 GPU Support OpenGL ES1.1/2.0, OpenVG1.1
VPU	Support 4K VP9 and 4K 10bits H265/H264 video decoding, up to 60fps 1080P multi-format video decoding (WMV, MPEG-1/2/4, VP9, H.264, H.265) 1080P video coding, support H.264/H.265 Video postprocessor: de-interlacing, denoising, edge / detail / color optimization
RAM	1GB/2GB/4GBDDR3
Storage	High-SpeedeMMC5.1（8GB/16GB/32GB/64GB/128GB） Support MicroSD (TF) Card Slot
NPU	Core-3328-JD4（AI）onboard AI neural network processor SPR2801S Computing power up to 2.8 Tops, 9.3Tops/Wultra-high efficiency Support PyTorch, Caffe framework, follow-up support TensorFlow Support for PLAI model training tools (currently support VGG-based GNet1, GNet18 and GNetfc network models)
Hardware Features
Ethernet	10/100/1000MbpsEthernet
WiFi	Provide SDIO 3.0 signal, support 2.4GHz / 5GHz dual-band WiFi, 802.11a/b/g/n/ac protocol
Display	1 x HDMI 2.0, support 4K@60Hz output 1x TV Out, in accordance with 480i, 576i standard
Audio	1 x SPDIF, for audio output 1 x I²S , support 8 channels
Interface	I2C, UART, SPI, SDIO3.0, USB2.0, USB3.0, I2S（Support 8-way digital microphone array input）
Power	DC input voltage 5V
OS/Software
OS	Android 、Linux
Appearance
Size	69.6mm × 49.6 mm
Type	Gold finger（SODIMM 260P, 0.5mmpitch）
PCB	6-layer board design