Introducing EmbeddingGemma Brand new open weights (under the slightly janky Gemma license) 308M parameter embedding model from Google:Based on the Gemma 3 architecture, EmbeddingGemma is trained on 100+ languages and is small enough to run on less than 200MB of RAM with quantization. It's available via sentence-transformers, llama.cpp, MLX, Ollama, LMStudio and more. As usual for these smaller models there's a Transformers.js demo (via) that runs directly in the browser (in Chrome variants) -...| Simon Willison's Weblog
Transform Your AI Experience with Ollama’s Game-Changing Desktop Application The wait is over! Ollama has officially launched its Ollama 0.1.0 desktop application for both macOS and Windows, marking a significant milestone in making local AI accessible to everyone. This groundbreaking release transforms how users interact with large language models, moving beyond command-line interfaces to deliver […]| Collabnix
Google’s Gemma AI models represent a significant breakthrough in open-source large language model development, offering developers and researchers unprecedented access to state-of-the-art natural language processing capabilities. This comprehensive technical guide explores Gemma’s architecture, performance benchmarks, implementation strategies, and practical applications in modern AI systems. What Are Google Gemma AI Models? Google Gemma is a family […]| Collabnix
この度、Google が開発するオープンモデル「Gemma」に焦点を当てた Gemma Meetup を開催いたします。本 Meetup は、参加者の皆様が Gemma の可能性や活用事例について知識を共有し、議論を深めることを目的としています。Gemma の技術的な詳細、活用方法、事例、今後の展望など、幅広いテーマを取り上げ、Gemma コミュニティの活性化を目指します。| Google Developers Japan