Gemma 4 E2B 推出 LiteRT-LM 端侧部署版本
原标题：litert-community/gemma-4-E2B-it-litert-lm
AI 摘要
Hugging Face 上发布 litert-community/gemma-4-E2B-it-litert-lm，将 Google 的 Gemma 4 E2B 模型以 .litertlm 格式打包，可直接部署在 Android、iOS、桌面、IoT 和 Web 端。该版本基于 LiteRT-LM 框架，采用 2bit/4bit/8bit 混合量化，纯文本场景权重内存占用可低至 0.8GB，并支持视觉与音频模型按需加载以进一步节省内存。其目标是让用户在设备端离线运行生成式 AI，保障隐私且无需联网。
正文节选
--- license: apache-2.0 base_model: - google/gemma-4-E2B-it tags: - litert-lm --- # litert-community/gemma-4-E2B-it-litert-lm Main Model Card: [google/gemma-4-E2B-it](https://huggingface.co/google/gemma-4-E2B-it) This model card provides the Gemma 4 E2B model in a way that is ready for deployment on Android, iOS, Desktop, IoT and Web. Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Thi