openfree

/

Gemma-3-R1984-27B-Q4_K_M-GGUF

like 7

input command (the file is downloaded into a local folder):
llama-cli --color -m /Downloads/GGUF/gemma-3-r1984-27b-q4_k_m.gguf -p "Hello, are you ready to serve?"
output Error message:
llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'gemma3' llama_load_model_from_file: failed to load model llama_init_from_gpt_params: error: failed to load model '/Downloads/GGUF/gemma-3-r1984-27b-q4_k_m.gguf' main: error: unable to load model