explainx / blog
Google's Gemma 4 E2B runs entirely on a Raspberry Pi 5 and Jetson Orin Nano inside the Open Duck Mini robot, enabling real-time multimodal AI with no cloud connection required.
Jun 26, 2026
Liquid AI's smallest model yet runs at 213 tok/s on a phone CPU and 42 tok/s on a Raspberry Pi 5. Pre-trained on 19T tokens with 32K context, it beats models twice its size on instruction following and tool use — and already controls a Unitree G1 humanoid on a Jetson Orin.
May 26, 2026
MiniCPM5-1B from Tsinghua researchers tops open-source AI charts at just 0.5GB. Explore how this breakthrough 1B parameter model beats larger competitors and enables truly local AI.
Jul 7, 2026
Ternlight puts semantic search on-device: text in, 384-dim vector out, cosine similarity for intent matching — all in ~7 MB in the browser. Here's how it works, when to use it, and how it compares to cloud embedding APIs.
TL;DR: At Google I/O 2026, two palm-sized bipedal robot ducks demonstrated what on-device AI looks like in practice: Gemma 4 E2B running on a Raspberry Pi 5 and an NVIDIA Jetson Orin Nano, processing speech, vision, and generating responses in real time—no cloud, no API calls, no latency tax. The ducks are based on the open-source Open Duck Mini v2 project by Antoine Piron, and the demo was led by Xavier Plantaz, Partner Solutions Engineer at Google. One of the ducks, asked to introduce itself, replied: "I am Autumn, a small duck robot's brain."
The Open Duck Mini (ODM) is an open-source, 3D-printable bipedal duck robot created by Antoine Piron and hosted on GitHub. It is directly inspired by Disney's BDX Droid—the small walking robot revealed at Star Wars Celebration—and costs roughly $400 in components to build from scratch.
The project's goal is simple: make legged robotics accessible to anyone with a 3D printer and basic electronics skills. Piron has released all hardware designs, firmware, and software under an open license, and the Google I/O 2026 demo represents the project's most high-profile moment yet.
Xavier Plantaz brought two ducks to the stage. Both were running Gemma 4 E2B entirely on-device, with no cloud connection:
| Duck | Hardware | Model |
|---|---|---|
| Duck A | Raspberry Pi 5 | Gemma 4 E2B on LiteRT |
| Duck B | NVIDIA Jetson Orin Nano | Gemma 4 E2B on LiteRT |
Both ducks are equipped with:
The ducks boot into an attention mode, an animated loop with LED expressions that signals the system is live and listening.
During the demo, Plantaz asked one of the ducks:
"Hey Gemma, explain me what a large language model is."
The duck responded:
"A large language model is a complex AI designed to understand and generate human-like text. I am here to assist you with tasks and interactions."
When asked to introduce itself:
"I am Autumn, a small duck robot's brain."
The name "Autumn" comes from ODM—the Open Duck Mini acronym, phonetically rendered. The response latency was described as "very snappy" by Plantaz, running entirely on local hardware.
The full on-device pipeline across both duck configurations:
Parakeet — NVIDIA's open ASR model handles transcription of the duck's microphone input into text, running locally without network access.
Gemma 4 E2B on LiteRT — Google's 2B-parameter edge model processes the transcribed text along with visual input from the camera. LiteRT (formerly TensorFlow Lite) handles model loading, memory management, and hardware acceleration, targeting GPU or NPU backends where available.
Kokoro — A lightweight open-source TTS model generates the duck's spoken audio output from Gemma's text response.
The entire stack runs on a single board computer in real time, with no external dependencies.
Gemma 4 was released on April 2, 2026 as Google's latest family of open-weight models under the Apache 2.0 license. The family includes:
The E2B variant is the one powering the ducks. Key specs:
The E2B's native multimodality is what makes the duck demo possible—the same model simultaneously understands speech tokens (from Parakeet's output), processes visual tokens from the camera, and generates a response, all in one forward pass pipeline.
Running AI inference locally on the robot rather than in the cloud changes the calculus for robotics in several meaningful ways:
Latency — No round-trip to a remote server. The duck responds in real time because the model is co-located with the sensors.
Privacy — Everything the camera sees and the microphone hears stays on-device. No audio or video is transmitted to any external service.
Connectivity independence — The duck works in a basement, a field, or anywhere without reliable internet. This matters enormously for autonomous robots operating in unstructured environments.
Cost at scale — Once the hardware is purchased, there is no per-query API cost. A fleet of 1,000 ducks running Gemma 4 E2B pays nothing per inference beyond electricity.
Plantaz described the current demo as the foundation, not the destination. The stated next steps:
The Open Duck Mini project is fully open source:
Gemma 4 E2B runs on LiteRT via the standard MediaPipe LLM Inference API, the same stack used for on-device inference on Android phones. If you can run it on a phone, you can run it on a Pi 5.
The Open Duck Mini demo at Google I/O 2026 is a proof of concept in the most literal sense: proof that a $400 hobby robot can carry a capable, multimodal AI model entirely on-device, respond conversationally in real time, and understand its visual environment—all running on a $80 single-board computer.
Three years ago, this required a GPU server and a cloud API. Today it runs on a duck. In June 2026, Liquid AI deployed LFM2.5-230M on a Unitree G1 humanoid — same on-device Jetson pattern, different scale: natural language decomposed into robot skill tool calls.
The models will keep getting smaller and faster. The hardware will keep getting cheaper. What the Open Duck Mini project shows is that the combination is already interesting enough to build with—and the next version might actually walk.
