Google DeepMind

At 740M parameters, it’s competitive across benchmarks – even outperforming some specialist models more than twice its size. Developers can use it to add multimodal search to their apps – like finding moments in a video using a voice memo – or pair it with Gemma 4 for private, on-device RAG. EmbeddingGemma 2 is released under an Apache 2.0 license. Check out the weights on @HuggingFace and @Kaggle. Find out more → https://t.co/lRsjbvR5VB