Update README.md

README.md

@@ -148,7 +148,7 @@ ggc la
 |  10| iq3_s  |  11.62±9|🐢🐢🐢🐢🐢🐢💨
 |  11| iq3_xxs|  12.08±9|🐢🐢🐢🐢🐢🐢🐢
 
-not all included in the initial test, the rest of them, test it yourself; btw, the interesting thing is: the loading time required was not aligning with file size, due to the complexity of each calculation (dequant), and might vary from model
+not all included in the initial test (*tested with a beginner laptop gpu only, if you have highend model, might find q8_0 running surprisingly faster than others), the rest of them, test it yourself; btw, the interesting thing is: the loading time required was not aligning with file size, due to the complexity of each calculation (dequant), and might vary from model
 
 ### **reference**
 - base model from [black-forest-labs](https://huggingface.co/black-forest-labs)