How to quantize llama with k-quant quantization?

[dbanka]

I could not find any documentation on how to do quantisation of llama model with new k-quant methods: q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K.

It will be very helpful if someone could share the steps/code to run that.

[dbanka]

Sorry it is already there in quantize help, found it