# Gemma architecture

A 4-bit quantized version of the Gemma 3 12B model, suitable for the MLX framework and supporting efficient text generation tasks.

A text generation model merged from Gemma-2B and Gemma-9B models using the SLERP method

A Chinese-English hybrid model based on the Gemma-2B architecture, integrating two specially optimized sub-models through the SLERP method

Magnolia-v3-Gemma2-8k-9B is a model created by merging pre-trained language models using mergekit, providing a new solution for text generation.

Hebrew-Gemma-11B-V2 is an open-source Hebrew/English pre-trained generative text large language model with 11 billion parameters, based on Google's Gemma-7B architecture.