Update README.md

README.md

@@ -77,9 +77,17 @@ Definitely set a "hard limit" for role play and/or chat.
 Different quants will give you slightly different prose, with higher quants giving strongest level of detail, "there"
 and nuance. Q4+ recommended.
 
-Q2k: If you use this quant you may need to lower temp (less then 1) and raise rep pen (1.08+) to address quality loss.
+Q2K: 
 
-IQ4XS: This might be the quant with the most difference compared to other quants.
+If you use this quant you may need to lower temp (less then 1) and raise rep pen (1.08+) to address quality loss.
+
+IQ4XS: 
+
+This might be the quant with the most differences (contrast creavity) compared to other quants.
+
+ARM QUANTS: 
+
+These quants are for specific systems that support this. If you use on a regular computer / GPU token per second will be VERY SLOW.
 
 Enjoy!