Google发布EmbeddingGemma 2模型
Google新发布的EmbeddingGemma 2能让手机本地处理多模态数据，无需上传服务器，还特别优化了代码搜索能力。
Google推出EmbeddingGemma 2模型，采用Apache 2.0许可证。该模型拥有740M参数，基于Gemma 4架构，支持文本、代码、图像、音频和视频的多模态处理。在Pixel 11 Pro上，量化文本权重占用191MB RAM，完整多模态模型占用567MB RAM。代码搜索性能显著提升，MTEB Code分数从68.76升至78.68。
Google dropped EmbeddingGemma 2 for on-device multimodal AI, under an Apache 2.0 license
> puts text, code, images, audio and video into 1 searchable space on phones. gives phones a missing piece: a way to understand and search your own stuff without sending it to a server.
> 740M parameters, uses the Gemma 4 architecture.
> Its parts are modular, so a text-only app needs just 270M parameters, while a 170M vision encoder and a 300M audio encoder load only when needed.
> On a Pixel 11 Pro, quantized text weights take about 191MB of active RAM, and the full multimodal model takes about 567MB.
> The context window grows 4x to 8K tokens, enough for roughly 5.5 minutes of audio, 29 images or 58 video frames in 1 input.
> Code search gained most, with the MTEB Code score rising from 68.76 to 78.68 while multilingual text scores held level.
> Google also claims top sub-1B results on audio and vision benchmarks and wins over some specialist models twice its size,
