Google open-sources EmbeddingGemma 2: a 270M-to-740M multimodal embedding model, 14% better on code retrieval, Apache 2.0
A small embedding model built on Gemma 4 that maps text, code, images, video and audio into one 768-dimensional space, bringing multimodal semantic search on device.
// Key points
- Load only what you need: 270M for text and code, 440M with vision, 570M with audio, 740M for all modalities; the text and code backbone has an 8,192-token context window.
- Outputs 768-dimensional vectors that can be truncated to 512, 256 or 128 via Matryoshka Representation Learning; 14% higher than EmbeddingGemma 1 on MTEB (Code) while keeping its multilingual text accuracy.
- On device, text-only weights use about 191 MB of active RAM and the full multimodal model about 567 MB on a Pixel 11 Pro, with INT4 and INT8 weights from quantization-aware training.
- Released under Apache 2.0 with weights on Hugging Face, and supported in Ollama, vLLM, Transformers, sentence-transformers, MLX, LiteRT and more.
Builder's takeThis one maps straight onto my AI Cloud Drive: with images, video, recordings and documents in one vector space, a single query can search across file types without a separate model per format. I'd swap the 270M text version in against my current embedder first, then load the vision module as needed; truncating to 128 dimensions cuts index storage, but measure the recall loss on your own retrieval set first.
// Background · from #Open models
Full timeline →- Oct 7 Mistral Large 4 enters public preview: 1T total, 49B active, $1.36 per million input tokens, weights by month end
- Oct 6 Aleph Alpha open-sources Kolibri: a 78B MoE with 3.46B active per token, validated to 1M-token context, Apache 2.0
- Oct 5 Ai2 open-sources AstaBrief 8B, which writes a cited research report in one pass, about 3.5x faster than its Claude-powered mode