AI news
公司内部站点 · 页面资源保存在本地（2026-10-17 18:30 UTC）· 独立 X 采集尚未配置；互动计数仅限本站

EmbeddingGemma 2 weights launch on Hugging Face and Kaggle with LiteRT and MediaPipe support

Google for Developers

Google for Developers made model weights for EmbeddingGemma 2 available on Hugging Face and Kaggle.

The model provides out-of-the-box integration support for LiteRT, MediaPipe, LangChain, and llama_index, as outlined in the EmbeddingGemma 2 developer guide.

#embeddinggemma#google-for-developers#hugging-face#model-weights

Google for Developers details offline execution and modular deployment for EmbeddingGemma 2

EmbeddingGemma 2 runs multimodal workloads entirely offline with zero server calls. The model features a modular design that lets developers drop unused vision or audio components to save memory, offers flexible dimension sizes that reduce local database storage by up to 6x, and pairs with Gemma 4 for efficient on-device RAG pipelines.