README.md

metadata

base_model:
  - google/gemma-3-27b-it-qat

gemma-3-27b-it-qat GGUF

Recommended way to run this model:

llama-server -hf ggml-org/gemma-3-27b-it-qat-GGUF -c 0 -fa

Then, access http://localhost:8080