RELEASE · MODELS · #2197
Google releases EmbeddingGemma 2 — compact multimodal embeddings for text, code, images, video, and audio
Google has released EmbeddingGemma 2, an open-weight multimodal embedding model based on Gemma 4 and licensed under Apache 2.0. The model produces unified 768-dimensional embeddings for text, code, images, video and audio, scales from ~270M to ~740M parameters depending on loaded encoders, supports Matryoshka Representation Learning (MRL) for truncated vectors, and is positioned for low-latency on-device search and retrieval; it is available on Hugging Face.
KEY POINTS
- Google has released EmbeddingGemma 2, an open-weight multimodal embedding model based on Gemma 4 and licensed under Apache 2.0.
- The model produces unified 768-dimensional embeddings for text, code, images, video and audio, scales from ~270M to ~740M parameters depending on loaded encoders, supports Matryoshka Representation Learning (MRL) for truncated vectors, and is positioned for low-latency on-device search and retrieval; it is available on Hugging Face.
- A compact, open multimodal embedding that unifies different media in one vector space and supports on-device deployment can simplify cross-modal retrieval pipelines and reduce storage/latency for local RAG and search applications.
WHY IT MATTERS
A compact, open multimodal embedding that unifies different media in one vector space and supports on-device deployment can simplify cross-modal retrieval pipelines and reduce storage/latency for local RAG and search applications.