Google has released EmbeddingGemma 2, an open 740-million-parameter model that turns text, images, video, audio, and code into numerical vectors. Google says it beats rival embedding models up to twice its size and runs locally via WebGPU.

Google Releases EmbeddingGemma 2

Google has released EmbeddingGemma 2, an open model that converts text, images, video, audio, and code into numerical vectors so similar content can be found and compared more easily. At 740 million parameters, Google says it is the most compact model of its kind and outperforms competing models up to twice its size on multimodal embedding benchmarks.

Benchmark Gains and Local Performance

EmbeddingGemma 2 scores 78.68 on the Massive Text Embedding Benchmark (Code), a jump of nearly 10 points over its predecessor, which scored 68.76. According to Google, that puts it on par with much larger models. The model runs locally without an API key, and each query takes about 20 to 70 milliseconds via WebGPU in the browser. It needs only around 191 MB of RAM and cuts local vector database storage by up to six times.

Offline RAG and Availability

For text-only tasks, Google says a 270-million-parameter version is enough. Paired with small open models like Gemma 4, EmbeddingGemma 2 can run offline RAG apps without sending data to external servers. The weights are available on Hugging Face and Kaggle, along with a developer guide and documentation.

Sources: The Decoder

Google Releases EmbeddingGemma 2, a Compact Multimodal Embedding Model