Вход на сайт

Просмотр новости

Найдите то, что Вас интересует

See what 3 builders are making with Gemma 4

Дата публикации: 09-06-2026 16:00:00

Here’s how three creators are building with Gemma 4, our latest and most advanced family of generative AI open models.

Основное содержимое страницы с новостью.

After 150 million downloads of Gemma 4, a few creations caught our eye. Here’s how three builders are using Gemma 4 to push creative boundaries and build new apps.


Amy Eisinger

Editorial & Content Communications Manager


Text saying Gemma 4 is in the center with photos surrounding of a piano, lion, music, a person, and an English tutoring app interface

Your browser does not support the audio element.

Listen to article

[[duration]] minutes

This content is generated by Google AI. Generative AI is experimental

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.

A user profile screen in the English tutoring app BetterSpeak

A screen in the BetterSpeak app to toggle on the Download Offline Mode

A user profile screen in BetterSpeak showing the offline pack application in progress

A screen showing the offline mode toggle turned on in a user's BetterSpeak profile settings

A screen in the BetterSpeak app showing tutoring instruction for talking about past experiences

A screen in the BetterSpeak app showing offline access to tutoring progress

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.

Get the latest news from Google in your inbox

Sign up for our newsletters with product updates, event information, special offers, and more.

Your information will be used in accordance with Google's privacy policy. You may opt out at any time.

Схожие новости

#Наименование новостиТональностьИнформативностьДата публикации
1Introducing Gemma 4 12B: a unified, encoder-free multimodal model019.0203-06-2026
2DiffusionGemma: 4x faster text generation09.4810-06-2026
3Gemma 4 QAT models: Optimizing model compression for mobile and laptop efficiency024.3605-06-2026
4Gemini API Managed Agents: 3.6 Flash, hooks, and more013.628-07-2026
5We’re expanding access to Gemini in Google Vids.5717-11-2025
6Google представила три новые ИИ-модели Gemini011.4823-07-2026
7Google расширила Gemini, но флагмана все еще нет. Кратко о нейросетях — 22.07.2026011.3222-07-2026
8How Frontier AI Companies Build AI Models0501-07-2026
9Google Builds A New Gemini Model Team As AI Investments Accelerate01006-08-2026
10Google представил новую открытую ИИ-модель Gemma 3 с поддержкой 140 языков0012-03-2025

Классификация: Пресс-релизы. Схожих патентов: 0. Схожих новостей: 10. Тональность: 0. Информативность: 19.07. Источник: blog.google.