Update README.md

README.md

@@ -41,5 +41,7 @@ for more info on imatrix handling see https://github.com/ggerganov/llama.cpp/pul
 | iq2_xs             | xxx |
 | iq2_xxs            | xxx |
 
-### Interesting observation
-despite `merge.imatrix` being different from `kalomaze-group_10_merged.172chunks.imatrix`, they produce the exact same quantized iq3_xxs model file. (same hash, checked multiple times)
+### Interesting observations
+despite `merge.imatrix` being different from `kalomaze-group_10_merged.172chunks.imatrix`, they produce the exact same quantized iq3_xxs model file. (same hash, checked multiple times)
+
+q5_k_m has a lower perplexity with the imatrix. but that probably is caused by kalomaze-group_10_merged diverging enough from wiki.