Quant	Size	Description
Q2_K	839.13 MB	Not recommended for most people. Very low quality.
Q2_K_L	1.1 GB	Not recommended for most people. Uses Q8_0 for output and embedding, and Q2_K for everything else. Very low quality.
Q2_K_XL	1.65 GB	Not recommended for most people. Uses F16 for output and embedding, and Q2_K for everything else. Very low quality.
Q3_K_S	954.59 MB	Not recommended for most people. Prefer any bigger Q3_K quantization. Low quality.
Q3_K_M	1023.52 MB	Not recommended for most people. Low quality.
Q3_K_L	1.06 GB	Not recommended for most people. Low quality.
Q3_K_XL	1.31 GB	Not recommended for most people. Uses Q8_0 for output and embedding, and Q3_K_L for everything else. Low quality.
Q3_K_XXL	1.86 GB	Not recommended for most people. Uses F16 for output and embedding, and Q3_K_L for everything else. Low quality.
Q4_K_S	1.15 GB	Recommended. Slightly low quality.
Q4_K_M	1.19 GB	Recommended. Decent quality for most use cases.
Q4_K_L	1.41 GB	Recommended. Uses Q8_0 for output and embedding, and Q4_K_M for everything else. Decent quality.
Q4_K_XL	1.95 GB	Recommended. Uses F16 for output and embedding, and Q4_K_M for everything else. Decent quality.
Q5_K_S	1.35 GB	Recommended. High quality.
Q5_K_M	1.37 GB	Recommended. High quality.
Q5_K_L	1.55 GB	Recommended. Uses Q8_0 for output and embedding, and Q5_K_M for everything else. High quality.
Q5_K_XL	2.09 GB	Recommended. Uses F16 for output and embedding, and Q5_K_M for everything else. High quality.
Q6_K	1.56 GB	Recommended. Very high quality.
Q6_K_L	1.7 GB	Recommended. Uses Q8_0 for output and embedding, and Q6_K for everything else. Very high quality.
Q6_K_XL	2.24 GB	Recommended. Uses F16 for output and embedding, and Q6_K for everything else. Very high quality.
Q8_0	2.02 GB	Recommended. Quality almost like F16.
Q8_K_XL	2.56 GB	Recommended. Uses F16 for output and embedding, and Q8_0 for everything else. Quality almost like F16.
F16	3.79 GB	Not recommended. Overkill. Prefer Q8_0.
ORIGINAL (BF16)	3.79 GB	Not recommended. Overkill. Prefer Q8_0.