Update README.md

README.md

@@ -57,7 +57,8 @@ I used the same float 32 version files to create this version as was used to cre
 
 [ https://huggingface.co/DavidAU/Psyonic-Cetacean-Ultra-Quality-20b-GGUF ]
 
-The main difference is the size 13B vs 20B, and this version's perplexity is much lower than the original or ultra versions.
+The main difference is the size 13B vs 20B, and this version's perplexity is much lower than the original or ultra versions 
+(q4KM: "Original 20B": PPL = 8.7858, "Ultra 20B": PPL = 8.6882, "Depth Charge": PPL = 7.1007 - lower is better.)
 
 This version will also be faster in per token per second generation too.