Feature 1: Built on the Proven reComputer RK3576 Module

Built on the reComputer RK3576 Module, the system brings the RK3576 computing platform into a compact, deployment-ready industrial computer.

• Advanced Processing Subsystem: Octa-core CPU architecture featuring 4× Cortex-A72 @ 2.2GHz + 4× Cortex-A53 @ 2.0GHz, paired with an ARM Mali-G52 MC3 GPU to handle demanding multi-threaded industrial control and automation tasks.
• Flexible Hardware Configurations (Optional): Available in multiple memory and storage combinations to perfectly align with your specific edge workload requirements:

Memory: 4GB / 8GB LPDDR5 (Scalable up to 16GB).

Storage: 32GB / 64GB eMMC(Scalable up to 128GB).

Feature 2: Next-Gen Edge AI Engine

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 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: Compact Fanless Design with Industrial Power

Designed for reliable operation in space-constrained industrial environments, featuring fanless passive cooling and a wide-range industrial power input.

• Fanless Passive Cooling
• Compact Metal Enclosure
• 9–36V DC Wide-Voltage Input
• 2-Pin Terminal Block
• DIN-Rail / Wall Mounting
• Operating Temperature: 0–60°C with 0.7 m/s airflow

Feature 4: Industrial I/O & Networking

Connect directly to PLCs, sensors, meters and field devices through built-in industrial communication and I/O interfaces, reducing the need for additional interface adapters.

• 2× RS485
• 1× CAN FD
• 1× DI/DO
• Dual Gigabit Ethernet（1 x PoE PD Support）

Feature 5: Pre-installed Armbian and Multi-OS

Pre-installed with Armbian and compatible with Ubuntu, Debian, Android and balenaOS, giving you the flexibility to choose the software environment that fits your application.

Feature 6: Flexible Expansion for Storage, AI & Wireless Connectivity

Adapt the system to different edge deployments with built-in M.2 and mini-PCIe expansion options.

• M.2 Expansion — Supports 2280 NVMe SSDs or AI accelerator modules
• mini-PCIe Expansion — Supports 4G, LoRaWAN and Wi-Fi HaLow modules

Feature 7: Faster AI Deployment with reComputer AI Lab

Accelerate AI evaluation and deployment on RK3576 with ready-to-use models, environments and deployment workflows. Please Click

• Ready-to-Run AI Models — CV / LLM / VLM / Speech
• Pre-Configured Docker Environments
• One-Command Model Deployment
• Guided Examples & Tutorials

Feature 8: 8K Multimedia & Ultra-HD Processing

• Video Decoding: Up to 8K @ 30fps (H.265 / H.264 / AV1 / AVS2).
• Video Encoding: Up to 4K @ 60fps (H.265 / H.264).

• Industrial Vision Inspection: Run local AI vision workloads for object detection, classification and automated inspection.
• Industrial Data Acquisition & Gateway: Connect field devices through RS485, CAN FD and digital I/O, process data locally and forward it to upper-level systems.
• Equipment & Energy Monitoring: Monitor machine status, meter data and operating conditions with local data processing and logging.