Gemma 2

Gemma 2 is Google DeepMind's family of open-weight language models available in 2B, 9B, and 27B parameter sizes, designed to be lightweight yet highly capable. The models achieve competitive performance against much larger models through novel architectural improvements including interleaving local and global attention layers. Gemma 2 is released under a permissive license and is optimized for deployment on consumer hardware, making it popular for local AI applications and fine-tuning.

Threads