See what 3 builders are making with Gemma 4

We recently released Gemma 4, our most capable open models to date. Since then, they have been downloaded more than 150 million times, and we’ve been expanding the family’s capabilities. We introduced Multi-Token Prediction (MTP) to accelerate inference, and recently released the 12B Unified model and Quantization-Aware-Training (QAT) checkpoints. Released under an Apache 2.0 license, Gemma 4 gives builders and organizations flexibility to fine-tune and deploy models across a variety of environments, from edge devices to local workstations.

Many builders are sharing what they’ve created with Gemma 4, showcasing how the models’ capabilities translate into real-world applications. Here are three highlights of what people and companies are creating.

Build low-latency, on-device apps.

The team at the app building company HubX used Gemma 4 to build BetterSpeak, an offline AI English tutoring platform. BetterSpeak uses the edge-optimized Gemma 4 E2B (effective 2B parameters) model as the reasoning engine for its on-device pipeline, enabling private, low-latency tutoring without the need for an internet connection.

To overcome mobile hardware constraints, HubX deployed the 4-bit quantized version of the model released by Google. This version handles tasks like grammar explanations and progress monitoring across multiple languages. By leveraging Gemma 4’s native audio input capabilities, the app supports direct speech-to-speech learning, reducing costs while ensuring user privacy by processing all vocal and text data entirely on-device.

Get creative with vision capabilities.

Gemma 4 can perform a wide range of vision-language tasks, like object detection, visual question answering (VQA), image captioning and reasoning across multiple images.

A builder who goes by @measure_plan on X used this capability by prompting Gemma 4 to perform VQA through a specific persona. The model effectively maintained a "medieval bard" character while accurately identifying objects in the room. As the builder takes different actions, Gemma 4 stays in the persona, identifying a "glass of amber liquid" and "shelves laden with bound tomes" without breaking character.

Gamify the world around you.

Gemma 4 makes processing long-form content easy, with the larger models offering a context window of up to 256K. This expanded memory is crucial for projects like the one created by @GOROman on X, who built an app that reimagines the real world as an adventure video game. In gaming, context is everything. The large context window allows the app to remember a long history of what’s recently happened in its world.

Gemma 4 sets a new standard and offers you a chance to build locally with maximum control. Try it in Google AI Edge Gallery on iOS or Android, or explore it in Google AI Studio.