Google 发布 EmbeddingGemma 2：740M 参数开源多模态嵌入模型
Google 出了 740M 的多模态嵌入模型，文本图片视频都能嵌入，还能配 Gemma 4 离线跑 RAG，权重直接可下。
Google 推出 EmbeddingGemma 2，是其首个开源的原生多模态嵌入模型。模型仅 740M 参数，可同时处理文本、代码、图像、视频和音频任务。官方称其性能超过部分体积两倍以上的专用嵌入模型。与 Gemma 4 搭配可用于离线、隐私优先的 RAG 场景，权重已在 Hugging Face 上开放下载。
Introducing EmbeddingGemma 2, a new open multimodal model that sets the standard for on-device efficiency. - our first open, natively multimodal embedding model - handles text, code, image, video, and audio tasks within a lightweight, modular 740M parameter form factor - ideal for offline, privacy-first RAG when paired with Gemma 4 - outperforms some specialist models more than twice its size Weights available now on Hugging Face. Your browser does not support the video tag. 🔗 View on Twitter 💬 139 🔄 161 ❤️ 1749 👀 89612 📊 235 ⚡
- Google DeepMind10-06 16:04原文
