Powered by SOPHON AI processor BM1684, this computer can be configured with 12GB large RAM. INT8 computing power is up to 17.6TOPS. It supports mainstream frameworks and complete toolchain with high usability, featuring low cost of algorithm migration. It can be applied to various AI scenarios, such as visual computing, edge computing, general computing power services, intelligent transportation, smart classes, unmanned supermarkets, security surveillance, UAV etc.

Specifications

Basic Specifications
SOC	SOPHON BM1684
CPU	Integrated high-performance ARM A53, 12nm lithography process, clock speed up to 2.3GHz
TPU	Built-in tensor computing module TPU, computing power up to: 17.6T (INT8) / 2.2T (FP32) / 35.2 T (INT8, enable winograd) TPU contains 64 NPU arithmetic units, each NPU contains 16 EU arithmetic units, 1024 EU in total Support mainstream programming frameworks, such as TensorFlow / Caffe / PyTorch / Paddle / ONNX / MXNet / Tengine / DarkNet
VPU	Up to 32-channel H.265/H.264 1080p@30fps video decoding 1080p@50fps video encoding MJPEG image encoding and decoding up to 1080P@480fps
RAM	6GB/12GB LPDDR4/LPDDR4X
Storage	32GB/64GB/128GB eMMC
Storage Expansion	M.2 SATA3.0 SSD（2242）×1 TFcard slot ×1
Hardware Specifications
Ethernet	1000Mbps Ethernet ×2
Wireless	2.4GHz/5GHz dual-band WiFi, 802.11a/b/g/n/ac expanded with 4G LTE (Mini PCIe interface), 5G (M.2)
Video Output	HDMI1.4（1080p@30fps）×1
Audio Output	HDMI1.4 audio output×1
SATA	M.2 SATA3.0 (expanded with 2242 SATA SSD) ×1
USB	USB3.0 (current limit: 1A) ×2 USB2.0 (current limit: 500mA) ×2
Power	DC12V (DC5.5×2.5mm)
Other Interfaces	RS232×1、RS485×1
OS/Software
OS	Support Linux
Firmware Upgrade	Upgrade firmwares through TF card
General
Size	210×130×44.5mm
Environment	Operating Temperature: -20℃～60℃ Storage Temperature: -20℃～70℃ Operating humidity: 10%～90% (non-condensing)