EmbeddingGemma
EmbeddingGemma is a 308-million-parameter multilingual text embedding model, lightweight yet powerful, optimized to run entirely on everyday devices such as phones, laptops, and tablets, enabling fast, offline embedding generation that protects user privacy. Built on the Gemma 3 architecture, it supports over 100 languages, processes up to 2,000 input tokens, and leverages Matryoshka Representation Learning (MRL) to offer flexible embedding dimensions (768, 512, 256, or 128) for tailored speed, storage, and precision. Its GPU-and EdgeTPU-accelerated inference delivers embeddings in milliseconds, under 15 ms for 256 tokens on EdgeTPU, while quantization-aware training keeps memory usage under 200 MB without compromising quality. This makes it ideal for real-time, on-device tasks such as semantic search, retrieval-augmented generation (RAG), classification, clustering, and similarity detection, whether for personal file search, mobile chatbots, or custom domain use.
Learn more
Gemini Embedding
Gemini Embedding’s first text model (gemini-embedding-001) is now generally available via the Gemini API and Gemini Enterprise Agent Platform, having held a top spot on the Massive Text Embedding Benchmark Multilingual leaderboard since its experimental launch in March, thanks to superior performance across retrieval, classification, and other embedding tasks compared to both legacy Google and external proprietary models. Exceptionally versatile, it supports over 100 languages with a 2,048‑token input limit and employs the Matryoshka Representation Learning (MRL) technique to let developers choose output dimensions of 3072, 153,6, or 768 for optimal quality, performance, and storage efficiency.
Learn more
Gemini 3.5 Pro
Gemini 3.5 Pro is Google’s anticipated next-generation Pro model in the Gemini 3.5 series, designed for advanced reasoning, coding, multimodal understanding, and agentic workflows. It is expected to build on Google’s Gemini 3 family with stronger performance for complex tasks that require planning, context handling, tool use, and deep problem solving. The model is aimed at users who need more power than faster Flash models for demanding development, research, automation, and enterprise AI use cases. Gemini 3.5 Pro is expected to support sophisticated workflows across text, code, files, multimodal inputs, and connected tools. Developers and organizations will likely use it through Google’s AI platforms for building assistants, agents, coding tools, analysis systems, and productivity applications. As an upcoming Pro-tier model, Gemini 3.5 Pro is positioned for high-value workloads where accuracy, reasoning quality, and advanced task execution matter more than maximum speed.
Learn more
Universal Sentence Encoder
The Universal Sentence Encoder (USE) encodes text into high-dimensional vectors that can be utilized for tasks such as text classification, semantic similarity, and clustering. It offers two model variants: one based on the Transformer architecture and another on Deep Averaging Network (DAN), allowing a balance between accuracy and computational efficiency. The Transformer-based model captures context-sensitive embeddings by processing the entire input sequence simultaneously, while the DAN-based model computes embeddings by averaging word embeddings, followed by a feedforward neural network. These embeddings facilitate efficient semantic similarity calculations and enhance performance on downstream tasks with minimal supervised training data. The USE is accessible via TensorFlow Hub, enabling seamless integration into various applications.
Learn more
