Google DeepMind 发布 Gemma 3n：移动端多模态模型，支持弹性推理
原标题：Introducing Gemma 3n: The developer guide
AI 摘要
Google DeepMind 正式发布 Gemma 3n，这是一款面向移动端和边缘设备的开源多模态模型，基于 MatFormer 架构，支持弹性推理和自定义模型尺寸。该模型引入了 Per-Layer Embeddings 和 KV Cache Sharing 等技术，以提升设备端性能和长输入处理效率。Gemma 3n 支持多种开发工具，并提供了预提取模型和 Mix-n-Match 自定义功能，旨在赋能开发者构建端侧 AI 应用。
正文节选
The first Gemma model launched early last year and has since grown into a thriving Gemmaverse of over 160 million collective downloads. This ecosystem includes our family of over a dozen specialized models for everything from safeguarding to medical applications and, most inspiringly, the countless innovations from the community. From innovators like Roboflow building enterprise computer vision to the Institute of Science Tokyo creating highly-capable Japanese Gemma variants, your work has shown