Models

A new collection of open translation models built on Gemma 3, helping people communicate across 55 languages.

An optimized version of Google's TranslateGemma-12B-it (Gemma 3) designed for high-fidelity translation. This build features hard-coded Temperature=0.1 and English Anchor support to eliminate output redundancy and maximize accuracy.

TranslateGemma is a family of lightweight, state-of-the-art open translation models from Google, based on the Gemma 3 family of models. TranslateGemma models are designed to handle translation tasks across 55 languages.

Pütchi es un traductor offline Español↔Wayuunaiki que extiende el modelo TranslateGemma de Google DeepMind para incluir, por primera vez, la lengua originaria más numerosa del norte de Suramérica.

This model is created based on gemma3:27b. It was created for the purpose of translating English documents into Korean.

This model inherited from gemma3:4b for translation purposes(Educative Purpose) to tamil.

gemma-2-2b-jpn-it-translate is a model tuned for translation tasks based on google/gemma-2-2b-jpn-it released by Google.

This model, based on the gemma3 model, is specifically designed to perform high quality translations between multiple languages.