reComputer RK3576 Module Dev Kit: Rockchip RK3576 6 TOPS Edge AI Platform

The reComputer RK3576 Module Dev Kit combines the RK3576 Compute Module and a feature-rich IO Board into a complete development platform for edge AI prototyping and system validation.

Powered by an 8-core CPU and 6 TOPS NPU, the kit provides M.2 expansion, Gigabit Ethernet with PoE PD, HDMI, USB-C DisplayPort, MIPI DSI, MIPI CSI, USB, GPIO, audio, and storage interfaces, enabling developers to quickly evaluate computing performance, AI workloads, peripherals, and system architecture.

Together with reComputer AI Lab, developers can accelerate the deployment of computer vision, large language models, vision-language models, and speech AI before moving to custom carrier board development.

Feature1. Complete RK3576 Evaluation Platform

Move from a bare compute module to a complete development platform without designing a custom carrier board at the beginning of your project.

The Dev Kit combines the RK3576 Compute Module with an IO Board that exposes the module's key interfaces through standard connectors, allowing developers to evaluate hardware, software, peripherals, and system architecture on one platform.

Key Benefits:

• RK3576 Compute Module and IO Board in one kit
• Ready for hardware and software evaluation
• Simplifies peripheral and interface validation
• Reduces early-stage custom carrier board development
• Provides a reference platform for future product integration

Use the Dev Kit to validate the system first, then move to a custom carrier board when the product architecture is confirmed.

Feature2. 8-Core Computing with 6 TOPS Edge AI

At the core of the Dev Kit is the RK3576 processor, combining heterogeneous CPU computing with dedicated hardware AI acceleration.

8-Core CPU

The reComputer RK3588 features an advanced CPU architecture with

• 4 × Cortex-A72 @2.2GHz
• 4 × Cortex-A53 @2.0GHz
• LPDDR5 (4GB/8GB/16GB)
• ARM Mali GPU-G52 MC3

6 TOPS NPU

With a built-in 6 TOPS NPU, it delivers efficient AI inference directly on the device, reducing latency and enhancing privacy without relying on the cloud.

AI performance highlights include:

• Vision CNN: YOLO11@77.9FPS(640\*640)
• LLM: capable of deepseek-r1-distill-qwen 7b support
• VLM: capable of qwen2.5-vl 3b
• STT: whisper_base_20s (RTF 0.218) with real-time processing support
• TTS：mms_tts_eng_200 （RTF 0.069) with real-time processing support

Check the details of the benchmark.

Feature 3. reComputer AI Lab for Faster AI Deployment

The Dev Kit is supported by reComputer AI Lab, providing a streamlined workflow for model conversion, deployment, and evaluation on the RK3576 platform.

It supports a wide range of edge AI workloads, including:

• Computer Vision: Object detection, segmentation, tracking, and video analytics
• LLM & VLM: Local language and multimodal AI applications with models such as DeepSeek and Qwen
• Speech AI: Offline speech recognition and voice interaction with models such as Whisper

With containerized and simplified deployment workflows, reComputer AI Lab reduces environment setup and helps developers move from AI models to on-device evaluation faster.

Feature4. Rich I/O and High-Speed Expansion

The Dev Kit exposes a broad range of RK3576 interfaces for connecting storage, displays, cameras, networking, sensors, and other embedded peripherals.

M.2 NVMe Storage and AI Expansion

The onboard M.2 M-Key 2280 slot provides PCIe 2.1 ×1 connectivity.

It can be used with:

• SSD
• M.2 AI accelerator

This makes it easy to expand storage capacity or evaluate additional hardware acceleration during product prototyping.

40-Pin GPIO Expansion

A 40-pin GPIO expansion header provides convenient access to general-purpose interfaces for connecting sensors, actuators, controllers, and other embedded peripherals.

It enables developers to quickly build physical prototypes without designing additional interface hardware during early-stage validation.

Additional Native Interfaces

The Dev Kit also provides interfaces including:

• USB；GPIO；Audio；Storage；MIPI CSI；MIPI DSI；HDMI；USB-C DisplayPort；Gigabit Ethernet

Feature 5: Unlock the Raspberry Pi Expansion Ecosystem

This Dev Kit supports compatible Raspberry Pi peripherals

• Vision: Raspberry Pi Camera Module 3
• Display: Official 7-inch DSI Display
• Power & Expansion: PoE+ HAT and other compatible accessories

Build flexible solutions for machine vision, interactive displays, and Power over Ethernet applications.

Feature6. Gigabit Ethernet with PoE PD

The Dev Kit provides a native Gigabit Ethernet RJ45 port for high-bandwidth network connectivity.

Integrated IEEE 802.3at PoE PD support enables both power and network connectivity through a single Ethernet cable.

This is especially useful when prototyping smart cameras, AI terminals, gateways, and remotely deployed edge devices.

Feature7. High-Resolution Video Processing

The RK3576 integrates dedicated video processing hardware for high-resolution multimedia and vision applications.

Video Decoding

Supports up to:

• 8K @ 30fps: H.265 / VP9 / AV1 / AVS2
• 4K @ 60fps: H.264

Video Encoding

Supports up to:

• 4K @ 60fps: H.265 / H.264

These capabilities make the platform suitable for high-resolution video analytics, smart cameras, multimedia terminals, and other video-intensive edge applications.

• Build Vision-Enabled Edge Products

• Prototype camera-based products for inspection, monitoring, retail analytics, and other real-time on-device vision applications.
• Create Private Multimodal AI Devices

• Develop local AI assistants that combine language, vision, and voice processing while keeping sensitive data on-device.
• Accelerate Custom Edge AI Product Development

• Validate the AI software stack and overall product architecture before moving from the Dev Kit to a custom carrier board.

reComputer RK3576 Module Schematic

reComputer RK3576 Module IO Board Schematic