auto-patch README.md

README.md

@@ -39,14 +39,13 @@ more details, including on how to concatenate multi-part files.
 | [GGUF](https://huggingface.co/mradermacher/Marengo_7B_SLERP-GGUF/resolve/main/Marengo_7B_SLERP.IQ4_XS.gguf) | IQ4_XS | 4.2 |  |
 | [GGUF](https://huggingface.co/mradermacher/Marengo_7B_SLERP-GGUF/resolve/main/Marengo_7B_SLERP.Q4_0.gguf) | Q4_0 | 4.4 | fast, low quality |
 | [GGUF](https://huggingface.co/mradermacher/Marengo_7B_SLERP-GGUF/resolve/main/Marengo_7B_SLERP.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
-| [GGUF](https://huggingface.co/mradermacher/Marengo_7B_SLERP-GGUF/resolve/main/Marengo_7B_SLERP.IQ4_NL.gguf) | IQ4_NL | 4.4 | slightly worse than Q4_K_S |
+| [GGUF](https://huggingface.co/mradermacher/Marengo_7B_SLERP-GGUF/resolve/main/Marengo_7B_SLERP.IQ4_NL.gguf) | IQ4_NL | 4.4 | prefer IQ4_XS |
 | [GGUF](https://huggingface.co/mradermacher/Marengo_7B_SLERP-GGUF/resolve/main/Marengo_7B_SLERP.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
 | [GGUF](https://huggingface.co/mradermacher/Marengo_7B_SLERP-GGUF/resolve/main/Marengo_7B_SLERP.Q5_K_S.gguf) | Q5_K_S | 5.3 |  |
 | [GGUF](https://huggingface.co/mradermacher/Marengo_7B_SLERP-GGUF/resolve/main/Marengo_7B_SLERP.Q5_K_M.gguf) | Q5_K_M | 5.4 |  |
 | [GGUF](https://huggingface.co/mradermacher/Marengo_7B_SLERP-GGUF/resolve/main/Marengo_7B_SLERP.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
 | [GGUF](https://huggingface.co/mradermacher/Marengo_7B_SLERP-GGUF/resolve/main/Marengo_7B_SLERP.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
 
-
 Here is a handy graph by ikawrakow comparing some lower-quality quant
 types (lower is better):