How to convert FP16 gguf model to 4bit or 5 bit gguf model

[RakshitAralimatti]

I am able to convert the models to fp16 gguf models but facing issue in converting them further in 4bit or 5bit can any one help me to achieve this?

[micsthepick]

./llama-quantize ../text-generation-webui/models/biblegpt-unsloth/biblegpt-unsloth.F16.gguf  2

the above command works for me?
(2 comes from ./llama-quantize --help)

[cshamis]

% llama-quantize ../models/model_f16.gguf ../models/model_Q4_K_M Q4_K_M