Google releases EmbeddingGemma 2, a lightweight multimodal embedding model for on-device search

Google released EmbeddingGemma 2, a 740M-parameter multimodal embedding model under Apache 2.0 for private, on-device search and retrieval.

It maps text, code, images, video, and audio into one shared space and reports a 9.92-point gain over EmbeddingGemma 1 on MTEB Code.

The post lists about 191MB active RAM for quantized text-only weights and about 567MB for the full multimodal model on a Pixel 11 Pro.