EmbeddingGemma
Google's compact open embedding model, a miniaturised relative of Gemini, that turns text into meaning-carrying vectors for search understanding.
EmbeddingGemma is Google's open, multilingual embedding model — effectively a miniaturised relative of Gemini, the system behind Google's advanced search. Because Gemma is the open "little sister" of Gemini, EmbeddingGemma is a rare public window into the kind of representations Google's search infrastructure relies on.
Its specs are built for practical use: about 308M parameters (small enough to run on-device), a 2K-token context window, 768-dimensional output vectors, and support for 100+ languages, with state-of-the-art quality for its size. It uses encoder-style bidirectional attention, optimised for understanding rather than generation.
A standout feature is Matryoshka Representation Learning, which lets the 768-dim output be truncated to 512, 256 or 128 dimensions with little quality loss — trading accuracy for speed and storage on demand. We use Gemma-family embeddings across our own work, including query fan-out.
Related concepts
Mentioned in
-
Chrome Decisions API: the prompts, limits, engines and code reviews behind DecisionModel
Chrome's DecisionModel API landed on 6 to 8 October 2026. The exact prompts, limits, engine status and review findings, plus a comparison with Google's MediaPipe DecisionMaker and local tests of EmbeddingGemma 1, EmbeddingGemma 2 and Laya.
-
A free 300M model predicts Gemini's embeddings at 0.83 cosine
Mapping Gemma embeddings to Gemini embeddings via a linear transform recovers entity vector structures with high fidelity without calling the paid API.
