Tamas05/

gemma-3-27b-it-8bit-gguf

It is the GGUF converted version of the Google Gemma3 27B IT model (https://huggingface.co/google/gemma-3-27b-it).

Base Model: google/gemma-3-27b-it

Quantization: 8-bit (for efficient inference with relative accuracy)

Intended Use: Chatbots, text generation, creative writing, question-answering, just to mention a few, in 140 languages including Hungarian.