Make a sense of the new GGML Quantized Methods?

[JacobGoldenArt]

Hi, I've been using LLAMA-CPP-Python successfully on my M2 mac specifically. So far I've been only using Q4_0 versions of ggml models given the metal installation steps :

(5) Download a v3 ggml model
- ggmlv3
- file name ends with q4_0.bin - indicating it is 4bit quantized, with quantization method 0

But as I see from The Blokes model cards, There's a bunch of new quantized methods. I've read the descriptions of each method but not being a ML dev, I'm not really sure of the benefits of each and also if these knew methods are compatible with llama-cpp-python (specifically for mac (metal). Any thoughts Appreciated.

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
These new quantisation methods are only compatible with llama.cpp as of June 6th, commit 2d43387

Explanation of the new k-quant methods
The new methods available are:

GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type.

[bbecausereasonss]

I'm curious if/when we will get Metal support for these other types of GGML quants.