- VENTUNO Q runs fully autonomous and completely offline AI agents without external servers
- Dragonwing processor delivers up to forty dense TOPS of AI computing
- Robotics applications include vision-guided arms and autonomous machines that navigate complex environments.
Qualcomm and Arduino have launched Arduino VENTUNO Q, a single board computer designed for robotics, generative artificial intelligence and edge computing capable of operating completely offline.
The board uses the Qualcomm Dragonwing IQ8 series processor and a dedicated STM32H5 microcontroller for deterministic control, allowing systems to perceive, decide and act on the same device.
Qualcomm says the neural processing unit delivers up to 40 dense TOPS of compute, supporting simultaneous inference and complex processing locally, while 16GB of RAM and 64GB of expandable storage handle demanding multitasking.
Article continues below.
A new board designed for edge AI workloads
Fabio Violante, vice president and general manager of Arduino, said the platform enables “systems that not only interpret the world, but interact with it,” allowing machines to operate without relying on cloud connectivity.
The architecture integrates AI acceleration with real-time microcontroller logic, uniting perception, decision and actuation on a single board.
VENTUNO Q can run fully autonomous AI agents for tasks including offline voice assistants, gesture-responsive smart mirrors, and interactive kiosks in transportation hubs, healthcare counters, or resorts.
The system supports robotic applications, including pick-and-place robotic arms guided by vision and service robots capable of following people through dynamic spaces.
It also allows autonomous machines to navigate complex environments using Visual SLAM combined with path optimization.
Edge AI vision systems are also possible, enabling proactive safety monitoring, traffic observation, and automated quality inspections with local visual language models.
All of these functions are handled on the board, eliminating the need to transmit data to external servers.
VENTUNO Q runs Ubuntu and Debian Linux on its main processor and Arduino Core on Zephyr OS for real-time control.
Arduino App Lab supports Python scripts, Arduino sketches, and AI models out of the box, including gesture recognition and object tracking.
It also supports local LLMs powered by Qualcomm AI Hub, while Edge Impulse Studio allows training custom models.
Industrial I/O, multiple MIPI CSI camera connectors, audio, displays and 2.5Gb Ethernet provide comprehensive hardware compatibility.
“With VENTUNO Q, AI can finally move from the cloud to the physical world. This platform makes it possible to build machines that perceive, decide and act, all on a single board,” said Fabio Violante, vice president and general manager of Arduino, Qualcomm Technologies, Inc.
“Our goal is to make advanced robotics and cutting-edge AI accessible to all developers, educators and innovators. VENTUNO Q is the natural evolution of Arduino’s mission and an important step in bringing real-world intelligence to everyone.”
VENTUNO Q is compatible with Arduino UNO shields, Modulino nodes, Qwiic sensors and Raspberry Pi HAT expansions.
It will be available in Q2 2026 through the Arduino Store and other authorized resellers such as DigiKey, Farnell, Mouser Electronics and RS Components, although the board’s practical influence on existing platforms such as the Raspberry Pi remains uncertain.
Follow TechRadar on Google News and add us as a preferred source to receive news, reviews and opinions from our experts in your feeds. Be sure to click the Follow button!
And of course you can also follow TechRadar on TikTok for news, reviews, unboxings in video form and receive regular updates from us on WhatsApp also.
