EmbeddingGemma 2: an open, lightweight multimodal embedding model

Key points

• We introduced EmbeddingGemma last year to provide a lightweight option for high-quality text embeddings, to help your apps organize, search, and connect information directly on consumer hardware.1
• Today, we’re launching EmbeddingGemma 2, expanding beyond text to unify code, images, video, and audio in a shared embedding space.1
• Built from the same technology as Gemini Embedding models, EmbeddingGemma 2 is:1
• EmbeddingGemma 2 matches the strong multilingual text performance of EmbeddingGemma while delivering a significant 9.92-point improvement on code performance (in MTEB Code, from 68.76 to 78.68), making it well-suited for local codebase indexing, semantic code search, and coding agent retrieval.1

Sources (1)

• [1]EmbeddingGemma 2: an open, lightweight multimodal embedding model
  Google DeepMind Blog · Oct 6, 07:57 PM

  EmbeddingGemma 2: an open, lightweight multimodal embedding model

  We introduced EmbeddingGemma last year to provide a lightweight option for high-quality text embeddings, to help your apps organize, search, and connect information directly on consumer hardware.

Extractive summary: sentences quoted from the sources.