For Industry
Product Details
Wiki & Learn
Reviews
Download PDF

Feature

This product is more than an open-source 8-core Linux AI box. Built on the powerful Rockchip RK3576 8GB RAM, it is designed to make edge AI development and deployment faster and easier.
 
To improve the developer experience, Seeed offers reComputer AI Lab — a platform that helps you deploy AI applications with one-click tools and ready-to-use resources. It includes optimized edge AI model demos for CV, LLM, VLM, STT, and TTS, interactive tutorials, deployment tools, containerized applications, and community projects to speed up development on Rockchip.
 
With rich I/O, multiple OS support, wireless expansion options, and active cooling, this compact AI box is ready for a wide range of edge AI workloads.It is ideal for smart vision systems, voice-enabled devices, AI agents, robotics, and industrial edge applications.

Feature 1：Based on Powerful RK3576 Processor

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

Feature 2：6 TOPS NPU Embedded

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: [email protected](640*640)
  • LLM: capable for deepseek-r1-distill-qwen 7b support
  • VLM: capable for 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：Compute Power & Storage & Wireless Connectivity Expandable

It offers flexible expansion through
a) 1 × M.2 M Key: PCIe 2.1x1, supports SSD expansion and AI accelerators such as Hailo and Rockchip, up to 26TOPS
b) 1 x miniPCIe for wireless expansion, like 4G LTE, LoRaWAN, Wi-Fi HaLow

Feature 4：Broad Model & Framework Support

It also supports a wide range of popular AI models, From computer vision and speech to LLM-powered edge intelligence, including: YOLO, MobileNet V2, RetinaFace, CLIP, Whisper, DeepSeek-R1, Qwen2-VL，...................
Framework support includes: ONNX, PyTorch, TensorFlow, TensorFlow Lite, Caffe, Darknet，...................
Toolchain support: RKNN-Toolkit2
This broad compatibility makes it easy to migrate existing models and build integrated edge AI applications across Perception AI, Generative AI, Agent and Physical AI.

Feature 5：Get Started in Seconds with reComputer AI Lab

Deploying AI at the edge is often complicated — from environment setup and model conversion to performance optimization. To simplify this process, Seeed created reComputer AI Lab, a developer platform designed to lower the barrier to edge AI development.
It provides a complete collection of optimized AI model demos for CV, LLM, and VLM, along with interactive tutorials, deployment tools, containerized AI applications, project examples, and community resources. It is built to accelerate AI development and deployment on Rockchip, Raspberry Pi, and NVIDIA Jetson platforms.
For Rockchip users, reComputer AI Lab includes ：
  1. Ready-to-Use Models
Access pre-optimized models without starting from scratch. AI Lab includes models such as YOLO11, MobileNet, CLIP, and Whisper, optimized for Rockchip platforms. With the RKLLM toolchain, it also supports edge LLM deployment.
  1. One-Command Deployment Tools
Skip complex build environments and speed up deployment with one-command tools. With Seeed-optimized RKNN-Toolkit2, models can be converted from ONNX to NPU deployment in just minutes, making AI application deployment faster and easier.
  1. Comprehensive Tutorials, Projects, and Community
From basic NPU benchmarking to real-world applications such as YOLO11-based industrial detection, AI Lab provides step-by-step guides, practical project examples, and community support to help developers build faster.

Feature 6： Pre-installed Armbian and Multi-OS

The device comes with Armbian pre-installed for a fast out-of-the-box experience.
With the help of Armbian, we are able to provide long-term maintained system images, security updates, encrypted OS options, and OTA upgrade support for production-ready deployment.
It also supports multiple operating systems through the Rockchip ecosystem, giving developers more flexibility across different projects, Ubuntu, Android, Debian.
 

Feature 7：Simultaneous 3-Display Output with 8K Video Capability

The reComputer RK3576 Series supports simultaneous 3-display output, giving developers more flexibility for digital signage, control centers, smart retail, and multimedia systems.
Supported output interfaces include:
  • HDMI
  • MIPI DSI
  • Type-C (DP Alt Mode)
It also offers strong multimedia capabilities:
  • Up to 4K@60fps video encoding with H.265 / H.264
  • Up to 8K@30fps video decoding with H.265 / H.264 / AV1 / AVS2
This makes it ideal for high-resolution AI vision and multimedia applications.

Specification

ParameterDescription
Hardware Specification
reComputer RK3576reComputer RK3588
SKU4GB RAM：100062096
8GB RAM：100052518
16GB RAM：100042341		8GB RAM：100071234
16GB RAM：100086238
SOCRockchip RK3576Rockchip RK3588
CPU4x [email protected]
4x [email protected]		4x [email protected]
4x [email protected]
GPUARM Mali-G52 MC3ARM Mali-G610 MC4
NPUINT8@6TOPS; Supporting INT4/8/16/FP16/BF16/TF32 mixed operations
Operating SystemPre-installed: Armbian OS
Supported: Debian, Ubuntu
Customization: Android (subject to BSP adaptation), Yocto BSP
RAMLPDDR5: 4GB/8GB/16GBLPDDR5: 8GB/16GB/32GB
StorageNoneOptional 256GB eMMC*
System Specification
Power Input9V-19VDC
PoE (as powered device)1x PoE PD*
Button1x Power; 1x Recovery; 1x MaskROM
Interface
Ethernet1x Gigabit Ethernet
1x Gigabit Ethernet with PoE support*		1x 2.5 Gigabit Ethernet
1x 2.5 Gigabit Ethernet with PoE support*
USB1x Type A USB 3.0
3x Type A USB 2.0
1x Type C for OTG & DP		4x Type A USB 3.0
1x Type C for OTG & DP
GPIO1× 40-pin Expansion Header
Mini PCIe1× miniPCIe Slot
MIPI CSI2× 4-lane MIPI CSI (22-pin)
MIPI DSI1× 4-lane MIPI DSI (22-pin)
HDMI InputNone1× HDMI 2.0
HDMI Output1× HDMI 2.12× HDMI 2.1
SIM Card1x nano SIM Card Slot
SD Card1 x microSD card slot
M.2 Slot1x M.2 Key M 2280 slot (PCIe 2.1x 1), supporting either an NVMe SSD or an AI accelerator1× M.2 Key M 2280 (PCIe 3.0 ×4); 1× M.2 Key M 2242 (PCIe 2.1 ×1),
supporting either an NVMe SSD or an AI accelerator
LED1x Power; 1x Status; 1x User
Buzzer1None
Audio1x 3.5mm Headphone Jack with Microphone Input
Wireless Communication
Wi-FiOnboard WiFi6 & BT5.4 with FPC Antenna
BLE
LoRaUSB LoRa®*/SPI LoRa®*
Wi-Fi HaLowSPI Wi-Fi HaLow*
4G/5G Cellular4G LTE*
Standards
CertificationCE, FCC
TELEC
RoHS
REACH
KC
EUDOC, UKDOC
Ambient Conditions
Operating Temperature0~60°C0~55°C
Storage Temperature-20~90 °C-20~90 °C
Operating Humidity10~95% RH10~95% RH
Others
RTC1x 2PIN1x 2PIN
Dimensions122 × 92 × 54mm122 × 92 × 54mm
Heat DissipationHeatsink with Fan
Warranty1 year
Production LifetimeUntil January 2036
StatementOptions marked with * require additional purchase according to the accessories list.

Hardware Overview

Application

 
 
 
 
Check More Demos on reComputer AI lab.

Documents

Certification

HSCODE8471504090
USHSCODE8517180050
UPC
EUHSCODE8471707000
COOCHINA

Part List

reComputer RK3576-30
x1
12V/3A Power Adapter (with 1x US/EU/UK/AU Plugs)
x1
32GB microSD Card
x1
User Manual
x1

reComputer RK3576-30 | Open Rockchip AI Box tailored for AI Application Development

SKU 100052518
6 TOPS NPU | Open Source | 8 Core | LPDDR5 up to 16GB | Expandable to 26 TOPS via PCIe | M.2 for SSD & AI Acceleration | One Click Used with reComputer AI Lab | Armbian Pre-installed | CV, LLM, VLM，STT, TTS | miniPCIe for 4G/LoRaWAN/Wi-Fi Halow | Decoder 8K@30fps | Encoder 4K@60fps | Simultaneous 3-Display Output | 2x GbE
Type
Processor
RAM
eMMC
USD$199.00
Shipping and duties calculated at checkout.
  • Free Insurance Included On Us
  • Flexible Payments with PayPal Pay Later
  • Avoid Import Fees: Ship Tax-Free from Local Warehouses
  • 1 on 1 Support | 12-Month Warranty | 30-Day Return Policy