Gemma on Phones and Browsers: Research to Reality

AI Engineer10m 53s
Paige Bailey against a black background beside the blue and white headline “GEMMA GOES LOCAL”.
0 comments · 0 votesOpen discussionClose discussion
Sign in to join the discussion

    Paige Bailey introduces the Gemma model family and demonstrates ways to run small models close to the userOn-device inference runs a trained model on the user's device rather than relying entirely on a remote model service. rather than relying on a hosted service for every interaction. Browser and mobile examples cover text, images, audioA multimodal model can process or generate more than one kind of data, such as text, images and audio. and tool use, with deployment choices tied to device memory and available compute.

    The session connects these examples to developer tooling, including a browser storybook built with Transformers.js and a mobile model gallery. Bailey describes model sizes, quantizationModel quantization represents AI model values with fewer bits to reduce storage, memory use and often inference cost. and local execution options, while positioning broader DeepMind scientific work as context rather than claiming that every research capability is demonstrated on a phone.

    Original YouTube thumbnailWatch on YouTube

    Video topic coverage

    • Agents & workflows15
    • Coding & tools70
    • Models & learning80
    • Infrastructure & compute100
    • Research & evaluation15
    • Safety & security0
    • Business & productivity0
    • Creative & media0
    • Robotics & perception0
    • Society & policy0

    Share this video

    Paige Bailey against a black background beside the blue and white headline “GEMMA GOES LOCAL”. With WWW.ARTIFICIAL-INTELLIGENCE.VIDEO, 5 October 2026 and duration 10m 53s.

    Paige Bailey shows how small Gemma models can power browser and phone applications, using local demos to connect open-weight research with practical developer workflows.