Releasing RecurrentGemma - one of the strongest 2B-param open models designed for fast inference on long sequences and massive throughput! Both pre-trained and IT checkpoints available + code - try them out here! Code: Weights:

Introducing Gemma - a family of lightweight, state-of-the-art open models for their class built from the same research & tech used to create the Gemini models.  Demonstrating strong performance across benchmarks for language understanding and reasoning, Gemma is available worldwide starting today in two sizes (2B and 7B), supports a wide range of tools and systems, and runs on a developer laptop, workstation or @GoogleCloud. Excited to see what you’ll create →