Bring multimodal semantic search to the edge with EmbeddingGemma 2

Summary

Google DeepMind launched EmbeddingGemma 2, an open-weight multimodal embedding model that maps text, images, video frames, and audio into a single vector space. Designed for local, privacy-first applications, it runs on as little as ~191MB active RAM for text-only weights and ~567MB for the full multimodal model on a Google Pixel 11 Pro. The model powers two new interactive showcases in Google AI Edge Gallery: Instant Media Search, which retrieves local images and videos via natural language or example images, and Video Moments Finder, which locates specific visual moments in local video files without transcribing audio. Google AI Edge Foresight for Mac uses EmbeddingGemma 2 alongside Gemma 4 for local meeting note-taking, cross-modal retrieval, and live question answering. Optimizations include modular encoders, quantization-aware training to INT4/INT8, and Matryoshka Representation Learning slicing to reduce storage footprints by up to 8x.

Takeaways

1. 1

   EmbeddingGemma 2 is a 740M parameter multimodal embedding model that natively maps text, images, video frames, and audio into a single vector space, eliminating the need to chain separate captioning, speech-to-text, and text-embedding models.

2. 2

   The model can perform zero-shot intent routing without any training data or fine-tuning, matching user inputs directly against classification labels and labels in milliseconds.

3. 3

   Optimizations include modular encoders (load only needed modalities), quantization-aware training to INT4/INT8, and Matryoshka Representation Learning slicing that cuts local storage and index footprints by up to 8x.

FAQ