Update README.md

README.md

@@ -110,10 +110,10 @@ model-index:
 <img src=https://huggingface.co/alchemonaut/QuartetAnemoi-70B-t0.0001/resolve/main/anemoi.png>
 
 # QuartetAnemoi-70B-t0.0001-b4.6-h8-exl2
-Exl2 quant paramters: <br/>
-BPW: 4.6 <br/>
-Head Bits: 8 <br/>
-Fits in 48GB with 16K of context. <br/>
+Exl2 quant parameters: <br/>
+Bits per weight: 4.6 <br/>
+Head bits: 8 <br/>
+Fits in 48GB with 16K of context. Try 8 bit kvcache if you want 32K. <br/>
 
 A sequential merge using a custom algorithm (NearSwap) of:
 - [152334H/miqu-1-70b-sf](https://huggingface.co/152334H/miqu-1-70b-sf)