Update README.md

README.md

@@ -80,6 +80,8 @@ Here is the Bfloat16 repo (with a link to the Imatrix versions too) of this mode
 
 I suggest downloading the same quant(s) of the "Bfloat16" and "Float32" version and compare the two for your use case(s).
 
+Note the "character" of each model differs too.
+
 The Imatrix versions of this model have even lower perplexity (1/2 level of magnitude lower than this model, 1 full level of magnitude 
 lower than LLama3 Instruct) then both this model and Llama3 Instruct and enhanced output.