auto-patch README.md

README.md

@@ -43,14 +43,13 @@ more details, including on how to concatenate multi-part files.
 | [GGUF](https://huggingface.co/mradermacher/FrankenLimmy-10B-passthrough-GGUF/resolve/main/FrankenLimmy-10B-passthrough.IQ4_XS.gguf) | IQ4_XS | 6.1 |  |
 | [GGUF](https://huggingface.co/mradermacher/FrankenLimmy-10B-passthrough-GGUF/resolve/main/FrankenLimmy-10B-passthrough.Q4_0.gguf) | Q4_0 | 6.3 | fast, low quality |
 | [GGUF](https://huggingface.co/mradermacher/FrankenLimmy-10B-passthrough-GGUF/resolve/main/FrankenLimmy-10B-passthrough.Q4_K_S.gguf) | Q4_K_S | 6.4 | fast, recommended |
-| [GGUF](https://huggingface.co/mradermacher/FrankenLimmy-10B-passthrough-GGUF/resolve/main/FrankenLimmy-10B-passthrough.IQ4_NL.gguf) | IQ4_NL | 6.4 | slightly worse than Q4_K_S |
+| [GGUF](https://huggingface.co/mradermacher/FrankenLimmy-10B-passthrough-GGUF/resolve/main/FrankenLimmy-10B-passthrough.IQ4_NL.gguf) | IQ4_NL | 6.4 | prefer IQ4_XS |
 | [GGUF](https://huggingface.co/mradermacher/FrankenLimmy-10B-passthrough-GGUF/resolve/main/FrankenLimmy-10B-passthrough.Q4_K_M.gguf) | Q4_K_M | 6.7 | fast, recommended |
 | [GGUF](https://huggingface.co/mradermacher/FrankenLimmy-10B-passthrough-GGUF/resolve/main/FrankenLimmy-10B-passthrough.Q5_K_S.gguf) | Q5_K_S | 7.7 |  |
 | [GGUF](https://huggingface.co/mradermacher/FrankenLimmy-10B-passthrough-GGUF/resolve/main/FrankenLimmy-10B-passthrough.Q5_K_M.gguf) | Q5_K_M | 7.9 |  |
 | [GGUF](https://huggingface.co/mradermacher/FrankenLimmy-10B-passthrough-GGUF/resolve/main/FrankenLimmy-10B-passthrough.Q6_K.gguf) | Q6_K | 9.1 | very good quality |
 | [GGUF](https://huggingface.co/mradermacher/FrankenLimmy-10B-passthrough-GGUF/resolve/main/FrankenLimmy-10B-passthrough.Q8_0.gguf) | Q8_0 | 11.6 | fast, best quality |
 
-
 Here is a handy graph by ikawrakow comparing some lower-quality quant
 types (lower is better):