null

Cubie A7Z Tiny Size, Mighty AI SBC - Radxa

Radxa

No reviews yet Write a Review
SKU:
498-RS503-D1H0R42U0W28
MPN:
RS503-D1H0R42U0W28
Radxa Cubie A7Z – Compact AI Board with 1GB / 4GB / 8GB RAM for Robotics, IoT, and Edge Intelligence.
Radxa Cubie A7Z AI board with 1GB, 4GB, or 8GB RAM. Tiny yet powerful AI platform for robotics, IoT, computer vision, and intelligent automation applications. View full description
  • 100% Original Products
  • GST Invoice
  • Earn 3% Cashback
₹1,993.02 inc. GST
₹1,689.00 ex. GST
7 people looking at this.

Technical Specifications

Brand:
Radxa
SoC:
2x Arm Cortex-A76 up to 2.0GHz,6x Arm Cortex‑A55 up to 1.8GHz,1x Alibaba RISC-V XuanTie E902 up to 200MHz
GPU BXM-4-64 MC1:
Vulkan 1.3,OpenGL®ES 3.2,OpenCL 3.0
NPU Computing Power:
3TOPS
NPU Precision Support:
INT8 / INT16 / FP16 / FP32
Codec Video Encoder:
H.265 / H.264 up to 4K 30fps
Codec Video Decoder:
H.265 / VP9 / AVS2 up to 8K 24fps,H.264 up to 4K 30fps
RAM:
1GB - 2GB - 4GB - 6GB - 8GB - 16GB
Storage:
1x MicroSD Card Slot, 1x Optional onboard UFS storage,1x PCIe Gen3.0 1-lane (Supports NVMe SSD Expansion)
Video Output:
1x Micro HDMI 2.0 (Supports displays up to 4Kp60 resolution)
Video Input 1x MIPI Camera Interfaces:
Configurable as 1x 4-lane MIPI CSI or 2x 2-lane MIPI CSI, Ideal for AI vision applications
Network:
1x Onboard WiFi 6 / BT 5.4 with external antenna
USB:
1x USB 2.0 Type-C with Power and OTG,1x USB 3.1 Type-C with DP Alt Mode
Power:
1x USB 2.0 Type-C (5V/2A)
Button:
1x USB BOOT Button
GPIO:
40-Pin GPIO Header with I2C / SPI / PWM / I2S etc
Dimension:
65 mmX30 mm

Warranty Information

All the products supplied by Evelta are genuine and original. We offer 14 days replacement warranty in case of manufacturing defects. For more details, please visit our cancellation and returns page.

Description

Resources:

Datasheet

Radxa Cubie A7Z Ultra-Compact AI SBC: Power, Performance, and Portability in a Tiny Form Factor

The Radxa Cubie A7Z redefines compact computing with its ultra-tiny 65 x 30 mm design while offering performance that rivals larger single board computers. Powered by the Allwinner A733 SoC, this board integrates a high-performance octa-core CPU combining dual Arm Cortex-A76 cores and six Arm Cortex-A55 cores, along with the Imagination PowerVR BXM-4-64 MC1 GPU for advanced graphics. The built-in 3 TOPS NPU delivers seamless AI acceleration, making it an ideal choice for edge AI applications such as robotics, computer vision, image recognition, voice processing, and smart IoT devices.

Despite its small footprint, the Cubie A7Z ensures excellent mechanical compatibility, thermal stability, and reliable integration into space-constrained projects. Its energy-efficient design reduces latency by enabling AI inference directly at the edge, ensuring enhanced privacy and faster response times for real-time intelligent workloads. Whether you are building compact embedded solutions, portable devices, or AI-driven IoT systems, the Radxa Cubie A7Z provides unmatched versatility and performance in a miniaturised form.

Key Features of Radxa Cubie A7Z

  • Ultra-Compact Design: Measures only 65 x 30 mm, engineered for projects with limited space.

  • High-Performance CPU: Allwinner A733 SoC with octa-core hybrid architecture (dual Cortex-A76 + six Cortex-A55).

  • Advanced GPU: Imagination PowerVR BXM-4-64 MC1 for efficient graphics and rendering.

  • Integrated AI NPU: 3 TOPS INT8 Neural Processing Unit for accelerated machine learning at the edge.

  • Edge AI Applications: Optimised for robotics, smart vision, voice AI, IoT devices, and embedded automation.

  • Reliable & Compatible: Exceptional thermal stability, mechanical compatibility, and durability for long-term use.

Interfaces

Related Products