The Firefly AIO-1684XQ is a high-performance AI mainboard powered by the SOPHON BM1684X processor. It features up to 32TOPS of INT8 computing power, making it ideal for a variety of AI applications such as face recognition, video analysis, and object detection. Besides, it is another after AIO-1684XJD4 Firefly’s mainboard powered by SOPHON BM1684X processor. The AIO-1684XQ mainboard supports up to 32-channel 1080P H.264/H.265 video decoding, and can simultaneously process and analyze over 16-channel HD video. It also supports a variety of interfaces, including M.2 (5G), Mini PCIe, SATA3.0, Gigabit Ethernet, USB3.0, RS485, RELAY, and GPIO.
Firefly AIO-1684XQ BM1684X AI Mainboard Features
First of all, The Firefly AIO-1684XQ is perfect for a wide range of industries, including intelligent security, smart transportation, retail, finance, cities, industries, and energy. Its powerful computing capabilities and flexible deployment options make it an excellent choice for AI applications in diverse fields.
At the core of this mainboard lies the SOPHON AI processor BM1684X, featuring an octa-core ARM Cortex-A53 with a frequency of up to 2.3GHz and a 12nm lithography process. With up to 32Tops of INT8 computing power, 16TFLOPS of FP16/BF16, or 2Tops of FP32, it supports various programming frameworks, making it suitable for both cloud and edge AI inference applications. It is equipped with 16GB of RAM and 64GB of eMMC storage, providing ample memory for seamless and efficient processing.
The mainboard’s 32-channel H.265/H.264 1080P video decoding capability allows it to process and analyze over 16-channel HD video simultaneously. This feature is particularly useful for AI applications such as face detection and license plate recognition on video streaming, enhancing its potential for intelligent security solutions.
See also: Firefly CSA1-N8S1684X is an AI Server with 8 BM1684X Modules and 256TOPS
The AIO-1684XQ comes with a complete software and hardware package for effortless artificial intelligence inference. Its SOPHON SDK provides a wide array of software tools, including the underlying driver environment, compiler, and inference deployment tool. It supports mainstream frameworks like Caffe, TensorFlow, PyTorch, Paddle, ONNX, MXNet, Tengine, and DarkNet, allowing developers to work with their preferred tools.
Additionally, the mainboard supports multiple algorithms porting, making it highly adaptable for “person/vehicle/object” recognition, video structuring, and trajectory behavior. This level of versatility, combined with high security and reliability, makes it an excellent choice for various product development needs.
Moreover, the Firefly AIO-1684XQ offers a range of interfaces, such as M.2 (5G), Mini PCIe, SATA3.0, Gigabit Ethernet, USB3.0, RS485, RELAY, and GPIO. Besides, Firefly says that the AIO-1684XQ supports an industrial-grade connector for exceptional reliability and stability. The BTB interface enables a secure and seamless connection, enabling easy backplane integration to create a robust and powerful industrial motherboard.
Availability and price
There is no price information at the moment. Probably soon Firefly AIO-1684XQ AI Mainboard will be available for purchase from Firefly’s website.
Detailed features from the AIO-1684XQ specification
- SOC: SOPHON BM1684X
- CPU: High-performance octa-core ARM A53, 12nm lithography process, frequency up to 2.3GHz
- TPU: Built-in tensor computing module TPU, computing power up to: 32TOPS (INT8), 16TFLOPS (FP16/BF16), 2TFLOPS (FP32)
- Support mainstream programming frameworks: TensorFlow / Caffe / PyTorch / Paddle / ONNX / MXNet / Tengine / DarkNet
- VPU: 32-channel H.265/H.264 1080p@25fps video decoding
- 32-channel 1080P@25fps HD video processing(decoding + AI analysis)
- Support 12-channel H.265/H.264 1080p@25fps video encoding
- RAM: 16GB LPDDR4x
- Storage: 64GB eMMC 、128MB SPI Flash
- Ethernet: 2*1000Mbps Ethernet
- USB: 4 * USB3.0(Max:1A)
- Other Interfaces: M.2(5G)、Mini PCIe、SATA3.0、Gigabit Ethernet、USB3.0、RS485、RELAY、GPIO
- Power: DC 12V/5A(5.5mm*2.1mm)
- OS: Linux
- Dimension: 183mm * 105mm * 41.8mm
- Weight: ≈380g(Including heat sink)
- Environment: Operating Temperature: -20℃~60℃,Storage Temperature:-20℃~70℃,Operating humidity: 10%~90%(non-condensing)
Discussion about this post