Micro Server SE6-192
Datacenter
Micro Server SE6-192

SOPHON micro server SE6 is an edge computing product with high-performance, low-power consumption and powerful computing performance. Equipped with the third-generation TPU processor BM1684 independently developed by SOPHGO, SE6 has an INT8 computing power up to 211.2TOPS. It can process 192 channels of HD video at the same time and support 456 channels of full HD video hardware decoding and 24 channels of encoding.

$0.10
Add to Cart
Advanced Computational Power
Advanced Computational Power
Superior Computing Capabilities

Strong Computing Power
Support INT8 peak computing power up to 211.2T or 26.4T FP32  high-precision computing power

Excellent Computing Performance
Support 192-channel 1080P HD video whole-process processing and 456-channel full HD video hardware decoding and 24-channel encoding

High Computing Density
In the way of high-density integration and tight deployment, a single SE6 is equipped with 12*BM1684 to reduce TCO

Rapid Migration
Support Caffe/TensorFlow/PyTorch/ MXNet/Paddle Lite and other mainstream Deep learning frameworks

Versatile Adaptability
Versatile Adaptability
Robust Adaptive Features

Strong Adaptability
Working temperature ranging from  -5 ℃ to +45 ℃. Portable and mute design

Rich Algorithms
Support algorithm migration of pedestrian/vehicle / non-vehicle /  object recognition, video structurization, trajectory behavior analysis, etc.

Rich Scenarios
Widely used deployment in public security / traffic / industrial parks / producing / warehousing, etc. Flexible deployment in multiple fields and scenarios

Flexible Scalability
Multi-server cluster deployment,  Ethernet connection, unified management services and cloud deployment

Processor and Deep Learning
Processor and Deep Learning
Co-processor
ParameterDetails
Product Model
SE6 192-BA2-61
Deep Learning Capacity
211.2 TOPS, 26.4 TFLOPS
Deep Learning Co-processor
ARM A53 96-core @2.3GHz
Host Processor
ARM A53 8-core @2.3GHz
Video Decoding
H.264 & H.265: 11520fps @1080P
Video Encoding
H.264 & H.265: 600fps @1080P
JPEG Decoding
JPEG: 5760PCS/s @1080P
Video Decoding Resolution
8K / 4K / 1080P / 720P / D1 / CIF
Video Encoding Resolution
4K / 1080P / 720P / D1 / CIF
Storage & Other Features
Storage & Other Features
Deep Learning Framework
ParameterDetails
Device Memory
144GB LPDDR4X
Host Memory
12GB LPDDR4X
Storage
eMMC: 416GB
Interface
Ethernet: 3x 10/100/1000Mbps
Storage: Expandable 1 x 2.5-inch SATA hard drive
Other
1x UART(USB Type C), 1x Micro SD, 1x HDMI, 2x USB3.0
Power Supply
AC: 1 x 500W gold power supply, 100-240V~, 7-3.5A, 60-50Hz
Working Temperature
Temperature Range: -5°C ~ 45°C
Operation System
Linux: Ubuntu / Kylin
Deep Learning Framework
Models: PyTorch / ONNX / PaddlePaddle / TensorFlow / Caffe / MXNet / Darknet
Test1
Test 2
Test 3
Test 4
Origin
Elgota
Amazon
Best Buy
New Egg
Asus
Noon
Stripe
Amazon Pay
Paypal