An open, lightweight multimodal embedding model
EmbeddingGemma 2 is Google DeepMind's open embedding model that maps text, code, images, video and audio into one shared space, so you can search across them from a single query. At 740M parameters it runs on-device, needing about 567MB of RAM on a Pixel 11 Pro for the full multimodal model (191MB for text only). Apache 2.0 licensed, with weights on Hugging Face and Kaggle. MTEB Code score rises from 68.76 to 78.68.
Google EmbeddingGemma 2 launched on Product Hunt on 2026-10-12 and has 150 upvotes and 1 comments so far.
Pricing details for this tool haven’t been verified yet — check the tool’s website for current plans.