Update README.md

README.md

@@ -82,7 +82,8 @@ One version is not stronger than the other, they are different and result in dif
 
 <B>Recommended Quants:</B>
 
-This chart shows the order in terms of "BPW" for each quant with "IQ1_S" with the least, and "Q8_0" with the most:
+This chart shows the order in terms of "BPW" for each quant (mapped below with relative "strength" to one another) 
+with "IQ1_S" with the least, and "Q8_0" with the most:
 
 <small>
 <PRE>
@@ -100,6 +101,8 @@ More BPW mean better quality, but higher VRAM requirements (and larger file size
 The larger the model in terms of parameters the lower the size of quant you can run with less quality losses.
 Note that "quality losses" refers to both instruction following and output quality.
 
+Differences (quality) between quants at lower levels are larger relative to higher quants differences.
+
 (not all quants may be at this repo)
 
 Suggestions for this model: