EmbeddingGemma 2: An open, lightweight multimodal embedding model
Compiled by KHAO Editorial — aggregated from 2 sources. See llms.txt for citation guidance.
◎ Multiple-sources
EmbeddingGemma 2 is the most capable model for on-device multimodal embeddings, natively mapping combinations of text, images, audio, and video into a unified embedding space.
Key facts
- 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)
- Built on the Gemma 4 architecture and released under a commercially permissive Apache 2.0 license, EmbeddingGemma 2 has 740 million parameters, making it optimal for on-device inference
- When paired with generative models such as Gemma 4, EmbeddingGemma 2 enables on-device RAG pipelines that understand complex multimodal data
- Pair EmbeddingGemma 2 for local file retrieval with Gemma 4 for contextual reasoning
Summary
The team 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. Today, they're launching EmbeddingGemma 2, expanding beyond text to unify code, images, video, and audio in a shared embedding space. Built from the same technology as Gemini Embedding models, EmbeddingGemma 2 is:. Best-in-class for its size: Achieves leading scores among sub-1B multimodal embedders for its size across benchmarks like MTEB (Massive Text Embedding Benchmark) Code and MAEB (Massive Audio Embedding Benchmark), while matching or outperforming many larger models across text, vision, and audio tasks.