· AI Vision Processor RV1126B
· Deployment of Lightweight AI models
· Built-in 12-Megapixel ISP
· 4K High-Frame-Rate Video Decoding
· Multiple Video Input Interfaces
· Robust Network Capabilities
· Rich Expansion Interfaces
· Provides development materials
Debian
Buildroot+QT
Ubuntu
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
Deployment of AI models
Built-in 12-Megapixel ISP
4K Video Decoding
Multiple Video Input Interfaces
Robust Network Capabilities
Rich Expansion Interfaces
Development Materials
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.
It is widely used in facial recognition, access control gates, intelligent security systems, smart network cameras, smart peepholes/doorbells, and dash cams.

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 |
|
|
NPU |
3TOPS NPU, supporting INT4/INT8/INT16/FP16 mixed-precision computing |
|
|
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. |
|
|
Encoding/Decoding |
Encoding: 12M@30fps H.265/H.264 Decoding: 4K@30fps H.265/H.264 |
|
|
RAM |
LPDDR4 (1GB/2GB/4GB Optional) |
|
|
Storage |
eMMC (8GB/16GB/64GB Optional) |
|
|
Storage expansion |
1 × TF Card |
|
|
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) |
|
|
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. |
|
|
Size |
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 |
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 |
|
Firefly team, with over 20 years of experience in product design, research and development, and production, provides you with services such as hardware, software, complete machine customization, and OEM server.