Loading activity…
@googlegemma
The official home of Google's Gemma. Lightweight, state-of-the-art open models by Google DeepMind, built on Gemini tech. What will you build? 🚀💻
AI
AGI House plans limited on-site Jetson kit loans for builders whose Gemma projects must run entirely on-device.
AI
Google Gemma says seeding a canvas with a response template lets vLLM extract confidence scores and probability distributions for yes/no, multiple-choice and scored questions in one denoising step.
AI
The @googlegemma account says djev-run lets users experiment without their own GPU, at roughly $3 an hour and $0 when idle.
AI
A user reports testing the patch on a DGX Spark with almost no tuning. With one request at a time, the reported median (p50) latency was about 0.21 seconds.
AI
Google DeepMind hosts an SF gathering to mark the open models milestone.
