Google DeepMind releases open multimodal on-device embedding model EmbeddingGemma 2
Overview
Google DeepMind released EmbeddingGemma 2, an open 740M-parameter embedding model that maps text, code, images, video, and audio into one shared 768-dimensional space for on-device search and retrieval.
Reports describe it as the first natively multimodal model in the EmbeddingGemma line, and ModelScope reports it is released under Apache 2.0.
According to the released figures, text-only use needs about 191MB of active RAM when quantized on a Pixel 11 Pro, while loading all modalities takes about 567MB. On the MTEB Code benchmark, the model scores 78.68 NDCG@10, which the report says is about 14% above the first generation; on MTEB Multilingual v2 it scores 61.36, roughly flat compared with the earlier model. These benchmark and memory figures are as reported by the sources and have not been independently verified.
Written by AI from the articles below · updated Oct 9, 1:42 AM ET
Check the sources:
Article timeline
Follow the coverage from different perspectives. Times are ET.
- ModelScopeGoogle releases EmbeddingGemma 2, a lightweight multimodal embedding model for on-device search
AIGoogle 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.
- meng shaoGoogle DeepMind releases EmbeddingGemma 2, an open multimodal embedding model for on-device use
AIGoogle DeepMind released EmbeddingGemma 2, an open 740M-parameter embedding model that maps text, code, images, video, and audio into one 768-dimensional space. Text-only use needs a 270M-parameter footprint, about 191MB active RAM when quantized on a Pixel 11 Pro, while loading all modalities takes about 567MB. The reported MTEB Code NDCG@10 score is 78.68, about 14% above the first generation, and MTEB Multilingual v2 is 61.36, roughly flat.
Heat trend
Not enough continuous observations to show a trend yet.