From the source
From the source
Google releases multimodal embedding model for images, audio, and video
Google released EmbeddingGemma 2, an open multimodal embedding model that extends beyond text to images, audio, and video.
The 740-million-parameter model, built on the Gemma 4 architecture, scored 78.68 on the code section of the Massive Text Embedding Benchmark, nearly 10 points above its predecessor.
Model weights are available under an Apache 2.0 license from Hugging Face and Kaggle.
From the source
Google LLC today released EmbeddingGemma 2, an open multimodal embedding model small enough to run on a smartphone. The release takes the EmbeddingGemma line beyond text, which was all the first version handled when Google introduced it in September 2025 . Images, audio and video now share one embedding space with text.
siliconangle.com
