Update README.md

README.md

@@ -54,12 +54,12 @@ Q6_K_S : Q6_K
 
 Comparison:
 
-Quant |  size  |  PPL |   Comment
+Quant    |  size   |  PPL |   Comment
 ---------|---------|------|-----------
 Q4_K_M   |  18.1e9 | 11.0 | Q4 embed Q6 out
 Q4_K_H   |  18.0e9 | 11.0 | Hybrid quant with Q6 embed Q6 out
-Q6_K     | 24.6e9   | 10.7  | -
-Q6_K_H   | 22.5e9   | 10.7  | Hybrid quant with Q6_K embedding Q6_K output
+Q6_K     | 24.6e9  | 10.7  | -
+Q6_K_H   | 22.5e9  | 10.7  | Hybrid quant with Q6_K embedding Q6_K output
 
 The quant was evaluated for good reasoning performance across a curated set of test prompts. Experimenting with different
 quant levels determined this model to be quite sensitive to losing coherent reasoning ability when quantization to