Update README.md

README.md

@@ -5,16 +5,16 @@ EXL2 quants of [gemma-2-27b-it](https://huggingface.co/google/gemma-2-27b-it)
 
 My quants are meant to be a tight fit in 24 GB VRAM. Following VRAM usage numbers assume **8k context**.
 
-bpw|head|4 bit cache|16 bit cache
---:|--:|--:|--:
-👉 [**5.8**](https://huggingface.co/mo137/gemma-2-27b-it-exl2/tree/5.8_h8)|8 bit|21.85 GB|**23.69 GB**
-👉 [**6.5**](https://huggingface.co/mo137/gemma-2-27b-it-exl2/tree/6.5_h8)|8 bit|**23.81 GB**|25.65 GB
-👉 [**6.6**](https://huggingface.co/mo137/gemma-2-27b-it-exl2/tree/6.6_h6)|**6 bit**|**23.86 GB**|25.70 GB
+bpw|head|4 bit cache|16 bit cache|Notes
+--:|--:|--:|--:|:--
+[**5.8**](https://huggingface.co/mo137/gemma-2-27b-it-exl2/tree/5.8_h8)|**8 bit**|21.85 GB|**23.69 GB**|16 bit cache, but lower BPW
+👉 [**6.5**](https://huggingface.co/mo137/gemma-2-27b-it-exl2/tree/6.5_h8)|**8 bit**|**23.81 GB**|25.65 GB|👈 my recommendation
+[**6.6**](https://huggingface.co/mo137/gemma-2-27b-it-exl2/tree/6.6_h6)|6 bit|**23.86 GB**|25.70 GB|slightly higher BPW, but less precise head
 
 For this model the difference between 6 bit and 8 bit head is ~300 MB, it's not huge. It could be exchanged for about 0.1 bpw in the body.
 
 ---
-Check out turboderp's quants & `measurement.json`:  
+Check out turboderp's quants & measurement.json:  
 [3.00 bits per weight](https://huggingface.co/turboderp/gemma-2-27b-it-exl2/tree/3.0bpw)  
 [3.50 bits per weight](https://huggingface.co/turboderp/gemma-2-27b-it-exl2/tree/3.5bpw)  
 [4.00 bits per weight](https://huggingface.co/turboderp/gemma-2-27b-it-exl2/tree/4.0bpw)