AIO-1126BJD4 AI Motherboard

AIO-1126BJD4 AI Motherboard

$199.00

Taxes included. Shipping calculated at checkout.

Manual WikiDownload

Brand Firefly

Availability

7 in stock

Powered by Rockchip RV1126B quad-core AI vision processor with an integrated 3 TOPS NPU, it supports multiple AI models and deep learning frameworks. It features a 12MP ISP, 8MP AI-ISP, and various algorithm accelerators, supporting 12MP video encoding and 4K decoding with multiple input interfaces. Connectivity includes dual Ethernet, onboard Wi-Fi & Bluetooth, and optional 4G/3G expansion.

AI Processor RV1126B

Powered by the quad-core 64-bit RV1126B AI vision processor. The ARM Cortex-A53-based core operates at up to 1.6 GHz and includes NEON advanced SIMD and an FPU for enhanced high-performance computing and multitasking capabilities.

Deployment of Al Models

Supports private deployment of lightweight Transformer-based models under 2B parameters, including LLMs and multimodal models like Qwen, Gemma2-2B, Phi2, and MiniCPM series, to meet localized application needs in resource-constrained scenarios.

Built-in 12-Megapixel ISP

Equipped with a new-generation hardware-based ISP supporting up to 12MP, complete with accelerators for HDR, 3A, LSC, noise reduction, and other key algorithms. Building upon this foundation, an AI-ISP (up to 8MP), enabling superior spatial noise reduction and enhanced image processing capabilities.

4K Video Decoding

It handles video encoding at up to 12MP@30fps. Its multi-stream encoding capability allows for simultaneous high-resolution recording locally and low-resolution transmission to the cloud. It supports 4K@30fps decoding and includes an integrated JPEG codec with Baseline mode support for a variety of image sizes and YUV formats.

Multiple Video Input Interfaces

Supports 2× MIPI CSI/LVDS/SubLVDS D-PHY video input interfaces and 1× MIPI DSI video output interface, offering strong compatibility and stable, reliable transmission to meet diverse vision capture and display needs.

Robust Network Capabilities

Features dual Ethernet ports (1× Gigabit + 1× Fast Ethernet) with TSO/USO offload acceleration, along with an onboard Wi-Fi & Bluetooth module supporting dual-band 2.4GHz/5GHz Wi-Fi and Bluetooth 5.0, and expandable 4G/3G connectivity.

Rich Expansion Interfaces

Features expansion interfaces including MIPI-DSI, MIPI-CSI, RS485, RS232, I2C, UART, CAN, GPIO, USB 3.0, and USB 2.0, meeting peripheral expansion requirements for various scenarios.

Development Materials

Provides reference designs and comprehensive technical documentation for the baseboard, enabling users to efficiently conduct secondary development and rapidly build self-controlled products.

3 TOPS NPU Computing Power

Integrated 3 TOPS NPU supports mixed-precision computation (INT4/INT8/INT16/FP16) and mainstream deep learning frameworks like TensorFlow, PyTorch, and ONNX, enabling intelligent data processing, voice recognition, and image analysis to meet most edge AI application demands on terminal devices.

Application Scenarios

It is widely used in facial recognition, access control gates, intelligent security systems, smart network cameras, smart peepholes/doorbells, and dash cams.

Facial Recognition

Access Control Gates

Intelligent Security

Smart Network Cameras

Smart Peepholes/Doorbells

Dash Cams

Interfaces

Specifications

AIO-1126BJD4
Basic Specifications	SOC	Rockchip RV1126B
	CPU	Quad-core 64-bit ARM Cortex-A53, integrated with NEON and FPU, maximum main frequency of 1.6GHz
	ISP	12MP ISP, 8MP AI-ISP, integrated with multiple algorithm accelerators including HDR, 3A, LSC, 3DNR, 2DNR, sharpening, defogging, fisheye correction, gamma correction, feature point detection, etc.
	NPU	3TOPS NPU, supporting INT4/INT8/INT16/FP16 mixed-precision computing
	Decoding/ Encoding	Encoding: 12M@30fps H.264 Decoding: 4K@30fps H.264
	RAM	LPDDR4 (1GB/2GB/4GB Optional)
	Storage	eMMC (8GB/16GB/64GB Optional)
	Storage expansion	1 × TF Card
	OS	Debian12, Buildroot+QT, Ubuntu
	Software support	Supports private deployment of lightweight large language models and multimodal large models with up to 2B parameters under the Transformer architecture, such as small-sized large AI models including the Qwen series, Gemma2-2B, Phi2, InternLM2, MiniCPM series, TinyLLAMA, and RWKV7. Supports deep learning frameworks such as TensorFlow, TensorFlow Lite, PyTorch, Caffe, and ONNX.
	Power	DC 12V (5.5×2.1mm)
	Power consumption	Normal: 3.6W (12V/300mA), Max: 7.2W (12V/600mA), Min(Sleep): 0.84W (12V/70mA)
	Dimension	146.0mm × 102.21mm × 21.71mm
	Weight	≈127g
	Environment	Operating Temperature: -20℃ ~ 60℃, Storage Temperature: -20℃ ~ 70℃, Storage Humidity: 10%～90%RH (non-condensing)
Interface Specifications	Internet	Ethernet: 1 × Gigabit Ethernet (RJ45), 1 × 100M Ethernet (RJ45), supporting TSO (TCP Segmentation Offload) and USO (UDP Segmentation Offload) network acceleration WiFi: On-board WiFi & Bluetooth module, supporting 2.4GHz/5GHz dual-band WiFi and Bluetooth 5.0/4.2 4G: 4G/3G expandable via Mini PCIe
	Video input	2 × MIPI-CSI/LVDS/sub LVDS DPHY (Support 1/2/4Lane mode, 1Lane defaults to DO, and 2Lane mode defaults to DO/D1; 30P-0.5mm)
	Video output	1 × MIPI-DSI (1080P@60Hz, 1×4lanes; 40P-0.5mm)
	Audio output	2 × MIC IN (2Pin-2mm), 1 × SPK (2Pin-2mm), 1 × Headphone (3Pin-2mm)
	USB	1 × USB2.0 HOST (Max: 0.5A), 1 × USB3.0 DRD (Max: 1A), 1 × USB2.0 HOST (Wafer socket, 4Pin-2mm)
	Antenna	1 × WiFi/Bluetooth antenna
	Button	1 × Power, 1 × MaskRom, 1 × Reset
	Other interfaces	1 × SIM Card, 1 × Debug (3Pin-2mm), 2 × I2C (4Pin-2mm), 1 × GPIO pin header (20Pin-2mm), 1 × Phoenix terminal block (24Pin, 3.5mm pitch): 2 × RS485, 2 × RS232, 2 × CAN 2.0, 1 × UART, 3 × IO input, 3 × IO output