Google 称 EmbeddingGemma 2 性能超越两倍规模竞品嵌入模型
原标题：Google claims EmbeddingGemma 2 outperforms rival embedding models twice its size
AI 摘要
Google 发布开源多模态嵌入模型 EmbeddingGemma 2，可将文本、图像、视频、音频和代码转换为数值向量，参数量为 7.4 亿。Google 称其在多模态嵌入基准上优于参数量两倍的竞品，且无需 API key 即可本地运行，浏览器中通过 WebGPU 每次查询约 20 至 70 毫秒，仅需约 191 MB 内存，并可将本地向量数据库存储减少最多六倍。该模型搭配 Gemma 4 等小型开源模型可运行离线 RAG 应用，权重已在 Hugging Face 和 Kaggle 上发布。
正文节选
Google claims EmbeddingGemma 2 outperforms rival embedding models twice its size Google released EmbeddingGemma 2, an open model that converts text, images, video, audio, and code into numerical vectors so similar content can be found and compared more easily. At 740 million parameters, Google says it's the most compact model of its kind and outperforms competing models up to twice its size on multimodal embedding benchmarks. The model runs locally without an API key. Each query takes about 20 t