Update README.md

README.md

@@ -36,8 +36,8 @@ tags:
 - t/q1_0 and t/q2_0; doesn't work; encountering np.uint32(34 & 35) is not a valid GGMLQuantizationType error
 - q2_k is super fast; but picture looks like x-ray film; might be good for medical research or abstract stylist/artist
 - q3 family is very fast; finger problem can be easily detected but picture quality is interestingly good
-- notice the same file size in 0 and s models; still keep them all here; see who can help out to look into details
-- overall, q4 and above should be no problem for general to high quality production
+- notice the same file size in 0 and s models; still keep them all here; see who can help out to fix it
+- q4 and above should be no problem for general to high quality production
 
 ### Upper tier sets
 - sd3.5-[large](https://huggingface.co/calcuis/sd3.5-large-gguf) (recommended)