auto-patch README.md

README.md

@@ -36,10 +36,10 @@ more details, including on how to concatenate multi-part files.
 | [GGUF](https://huggingface.co/mradermacher/Fimbulvetr-10.7B-v1-i1-GGUF/resolve/main/Fimbulvetr-10.7B-v1.i1-IQ3_M.gguf) | i1-IQ3_M | 5.1 |  |
 | [GGUF](https://huggingface.co/mradermacher/Fimbulvetr-10.7B-v1-i1-GGUF/resolve/main/Fimbulvetr-10.7B-v1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 5.5 | IQ3_S probably better |
 | [GGUF](https://huggingface.co/mradermacher/Fimbulvetr-10.7B-v1-i1-GGUF/resolve/main/Fimbulvetr-10.7B-v1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 5.9 | IQ3_M probably better |
-| [GGUF](https://huggingface.co/mradermacher/Fimbulvetr-10.7B-v1-i1-GGUF/resolve/main/Fimbulvetr-10.7B-v1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 6.4 | almost as good as Q4_K_M |
+| [GGUF](https://huggingface.co/mradermacher/Fimbulvetr-10.7B-v1-i1-GGUF/resolve/main/Fimbulvetr-10.7B-v1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 6.4 | optimal size/speed/quality |
 | [GGUF](https://huggingface.co/mradermacher/Fimbulvetr-10.7B-v1-i1-GGUF/resolve/main/Fimbulvetr-10.7B-v1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 6.7 | fast, medium quality |
 | [GGUF](https://huggingface.co/mradermacher/Fimbulvetr-10.7B-v1-i1-GGUF/resolve/main/Fimbulvetr-10.7B-v1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 7.7 |  |
-| [GGUF](https://huggingface.co/mradermacher/Fimbulvetr-10.7B-v1-i1-GGUF/resolve/main/Fimbulvetr-10.7B-v1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 7.9 | best weighted quant |
+| [GGUF](https://huggingface.co/mradermacher/Fimbulvetr-10.7B-v1-i1-GGUF/resolve/main/Fimbulvetr-10.7B-v1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 7.9 |  |
 
 
 Here is a handy graph by ikawrakow comparing some lower-quality quant