RSQ11-EA delivers a low-latency compact Edge AI computing platform, capable of independently running AI models.
RSQ11-AIX, powered by the DeepX DX-M1 acceleration card, delivers a high-performance, low-latency edge computing platform. Welink provides stable, reliable, and rapidly deployable Edge AI solutions that extend AI capabilities from the cloud to the edge, enabling real-time decision-making and enhanced operational efficiency.
The system supports real-time image recognition, behavior analysis, object detection, and multi-channel video stream processing, making it ideal for applications such as smart surveillance, smart manufacturing, smart retail, and intelligent transportation.
| General | |
| CPU | Support Intel® Atom® Amston Lake processors (System design optimized for 6W/9W/12WCPU power consumption.) |
| Memory | DDR5 SO DIMM 8GB/16GB (option) |
| Mass Storage | eMMC 64G/128G/256G(option) |
| Power Input | Standard: 9~36V |
| Operation System | Windows® 10 IoT Enterprise Windows® 11 IoT Enterprise Linux |
| Basic I/O Interface | |
| Power Connector | DC Jack with Lock /4-Pin Terminal Block |
| Giga LAN | 2x 2.5 GbE LAN (Intel® i226-IT) |
| USB | 2x USB3.0 type A |
| Display | 2x HDMI |
| Expansion | 1x M.2 E Key 2230 |
| EMC Standard | |
| EMC Standard | CE/FCC Class A |
| Environmental | |
| Storage Temperature | -40°C ~ 85°C |
| Operating Temperature | -20°C ~ 50°C with airflow |
| Relative Humidity | 5 %~ 95 % (non-condensing) |
| Vibration | DIN Rail – 1G rms |
| Shock | Din-Rail – 15G half sign |
| Mechanical | |
| Degree of Protection | IP 30 |
| Dimension | 110mm (L) x 110mm (W) x 50 mm (H) |
| Net Weight | 0.8KG |
| Optional Accessories | |
| Power Adaptor | 4-pin Connector / DC Jack with Lock, 60W/24V |
| Mounting Kit | Din Rail mount, Wall mount |
| DeepX DX‑M1 AI Accelerator | |
| AI Performance | 25 TOPS |
| Form factor | Form Factor: M.2 M Key (22 x 80 mm) Interface: PCle Gen.3 x4 Memory: LPDDR4X/5 X16 4-channel, QSPI |
| Support S-O-T-A Algorithms | ResNet, MobileNet v1/v2/v3 SSD, EfficientNet, EfficientDet, YOLOv5, YOLOv7, YOLO8, DeepLabv3, PIDNet and the latest YOLO Models,VLM (CLIP etc.) |
| Support Framework | TensorFlow, TensorFlow Lite, ONNX, Keras, PyTorch by Dataflow complier converted |
| Support OS | Windows 11, 10 64bit Linux Ubuntu 22.04, 20.04 LTS Support Yocto Project and Docker |