ROC-RK3576-PC Overview Specifications Wiki Technical Case Download
Buy Now DataSheet
Buy Now DataSheet

ROC-RK3576-PC

Low-Power Large Model Mini Computer

Powered by the Rockchip RK3576, an octa-core 64-bit AIOT processor, ROC-RK3576-PC features a big.LITTLE architecture (4×A72 +4×A53)
and an advanced lithography process to deliver high performance while maintaining low power consumption. It is equipped with an
ARM Mali G52 MC3 GPU and a 6 TOPS NPU, supporting the private deployment of ultra-large parameter models under the Transformer
architecture. It is compatible with various deep learning frameworks, custom operator development,
and Docker container management technology. With an external watchdog,
it ensures industrial-grade reliability, making it an excellent choice for
AI applications requiring local deployment.

The private deployment of large models

Octa-core 64-bit AIOT processor RK3576

RK3576, the new octa-core 64-bit high-performance AIOT processor, features a big.LITTLE architecture (4×A72 +4×A53), an advanced
lithography process, and a frequency of up to 2.2 GHz. It ensures strong support for high-performance computing and multitasking.
With a Mali-G52 MC3 GPU delivering 145G FLOPS, this GPU is capable of supporting efficient heterogeneous computing to
meet the demands of graphics-intensive applications.

4K@120fps high frame rate video decoding

It supports 8K@30fps/4K@120fps decoding (H.265/HEVC, VP9, AVS2, and AV1) and 4K@60fps decoding (H.264/AVC), 4K@60fps encoding
(H.265/HEVC and H.264/AVC). With HDMI 2.1 (4K@120fps)/eDP1.3 (4K@60fps), DP1.4 (4K@120fps),
and MIPI DSI (2560* 1600@60fps) interfaces, it enables three-display output.

16MP ISP with enhanced image processing capabilities

The integrated 16-megapixel ISP supports low-light noise reduction, an RGB-IR sensor, and up to 120dB HDR.
It features AI-ISP technology to enhance image quality with reduced noise and offers support for MIPI-CSI input.

UFS 2.0 with a data read speed of up to 12Gbps

With support for UFS 2.0 / HS-G3 (12Gbps), this device ensures efficient data storage and access. With the PCIe NVMe/SATA SSD expansion,
it delivers rapid data read and write speeds, enabling the device to be easily expanded to TB storage capacity.

Credit card size and abundant interface options

A wide range of expansion interface options includes MIPI-CSI, MIPI DSI, USB 3.0, USB 2.0, I2C, SPI, SARADC, UART, PWM, LineOut,
and more. This device offers a 1000Mbps Ethernet port, dual-band 2.4/5GHz WiFi, and Bluetooth 5.0. Its compact design,
with dimensions of 90mm x 60mm, makes it highly adaptable for a wide range of applications.

Support various operating systems

Support Android 14, Linux OS, and Buildroot+QT. These provide a safe and stable system environment
for product research and production.

Abundant resources

We offer SDKs, tutorials, technical documentation, and development tools to streamline and improve the development process.

A wide range of applications

It is widely used in edge computing, local deployment of large models, intelligent digital signage,
cloud terminal products, industrial PCs, automotive electronics, and more.

Local deployment
of large models
Edge computing
Digital signage
Industrial PCs
Cloud terminal
products
Automotive
electronics

Specifications

Specifications
Basic Specifications SOC

Rockchip RK3576

Octa-core 64-bit processor (4×A72 + 4×A53), up to 2.2GHz
GPU

G52 MC3 @ 1GHz, supporting OpenGL ES 1.1/2.0/3.2, OpenCL 2.0, Vulkan 1.1

Built-in high-performance 2D acceleration hardware
NPU

6 TOPS NPU, supporting INT4/8/16/FP16/BF16/TF32 mixed operations
VPU

Decoding: 8K@30fps/4K@120fps: H.265/HEVC, VP9, AVS2, AV1, 4K@60fps: H.264/AVC

Encoding: 4K@60fps: H.265/HEVC, H.264/AVC
RAM

LPDDR4/LPDDR4x (4GB/8GB optional)
Storage

eMMC (16GB/32GB/64GB/128GB/256GB optional), UFS2.0 (optional)
Storage
Expansion

1 * M.2 (2242 PCIe NVMe/SATA SSD expansion ), 1 * TF card slot
Power

DC 12V (5.5mm * 2.1mm, 12V~24V wide input voltage)
OS

Android14, Linux OS, and Buildroot+QT
Software
Support

・ The private deployment of ultra-large-scale parameter models under the

Transformer architecture, such as Gemma-2B, LlaMa2-7B, ChatGLM3-6B, Qwen1.5-1.8B, and more.

・ Traditional network architectures such as CNN, RNN, and LSTM;

a variety of deep learning frameworks include TensorFlow, PyTorch, MXNet, PaddlePaddle, ONNX and Darknet.

・ Custom operator development.

・ Docker container management technology.
Power
Consumption

Normal: 1.2W(12V/100mA)，Max: 6W(12V/500mA)，Min: 0.096W(12V/8mA)
Size

93.00mm * 60.15mm * 12.49mm
Weight

≈50g
Environment

Operating temperature: -20℃- 60℃

Storage humidity: 10%～90%RH (non-condensing)
Interfaces Network

1 * Gigabit Ethernet (1000 Mbps / RJ45), 2.4GHz/5GHz dual-band WiFi (802.11a/b/g/n/ac), Bluetooth 5.0
Video Input

1 * MIPI CSI DPHY (30Pin-0.5mm, 1*4 lanes/2*2 lanes)
Video Output

1 * HDMI2.1(4K@120fps)、1 * DP1.4 (4K@120fps)、

1 * MIPI DSI DPHY（2560*1600@60fps，30Pin-0.5mm, 1*4 lanes）

Watchdog

External watchdog
USB

1 * USB3.0、1 * USB2.0
Expansion
Interface

1 * Type-C (OTG/DP1.4), 1 * FAN (4Pin-1.25mm), 1 * Debug (3Pin-2mm),

1 * 3.5mm Audio jack (supporting MIC recording, CTIA standard), 1 * MIC (2Pin-1.25mm)

1 * double-row pin header (20Pin-2.0mm): USB 2.0, I2C, SPI, SARADC, UART, and LineOut