Fogwise® AirBox
- Fogwise® AirBox
Products
Fogwise® AirBox is an embedded AI micro-server with arithmetic power up to 32TOPS@INT8, supports multiple precision (INT8, FP16/BF16, FP32), supports private GPT, text-to-image, and other mainstream AI model deployments, and is equipped with an aluminum alloy casing for deployment in harsh environments.
Characterization
| module | Fogwise® AirBox |
|---|---|
| sizes | 104 mm × 84 mm × 50.2 mm |
| processing unit | SOPHON SG2300X SoC，octa-core Arm® Cortex®-A53 (ARMv8) @ 2.3GHz |
| tensor processing unit | Tensor Processing Unit, computational power: up to 32TOPS (INT8), 16TFLOPS (FP16/BF16) and 2TFLOPS (FP32) Support for major deep learning frameworks including TensorFlow, Caffe, PyTorch, Paddle, ONNX, MXNet, Tengine and DarkNet. |
| memory | 16GB LPDDR4X |
| storage | 64GB eMMC 16MB SPI Flash High Speed SD Card Slot Available |
| multimedia | Supports decoding 32 channels of H.265/H.264 1080p@25fps video Fully handles 32 channels of HD 1080p@25fps video, including decoding and AI analytics Supports encoding 12 channels of H.265/H.264 1080p@25fps video JPEG: 1080p@600fps, max. Support 32768 x 32768 Support video post-processing, including image CSC, resize, crop, fill, border, font, contrast and brightness adjustment |
| interface | 2 Gigabit Ethernet ports (RJ45) 1 M.2 M-key slot for NVMe SSDs. |
| operating temperature | 0°C to 40°C |
| housings | Corrosion-resistant aluminum alloy housing |
| radiator | PWM speed control fan with custom heat sink |
Photograph of sth.
Chip block diagram
System block diagram
