Gemma 3n可用于设备端推理，配合RAG和函数调用库
Google has announced that Gemma 3n is now available in preview on the new LiteRT Hugging Face community, alongside many previously released models. Gemma 3n is a multimodal small language model...
谷歌宣布Gemma 3n在LiteRT Hugging Face社区预览，支持文本、图像、视频和音频输入。该多模态小语言模型有2B和4B参数变体，适合企业使用。Gemma 3n采用选择性参数激活技术，支持高效管理，并推出量化工具以减少模型大小和延迟。此外，还发布了AI Edge On-device Function Calling SDK，允许模型执行实际操作。
