auto-patch README.md

README.md

@@ -30,7 +30,7 @@ more details, including on how to concatenate multi-part files.
 | Link | Type | Size/GB | Notes |
 |:-----|:-----|--------:|:------|
 | [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-i1-GGUF/resolve/main/NoromaidxOpenGPT4-2.i1-IQ1_S.gguf) | i1-IQ1_S | 10.1 | for the desperate |
-| [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-i1-GGUF/resolve/main/NoromaidxOpenGPT4-2.i1-IQ1_M.gguf) | i1-IQ1_M | 11.1 | for the desperate |
+| [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-i1-GGUF/resolve/main/NoromaidxOpenGPT4-2.i1-IQ1_M.gguf) | i1-IQ1_M | 11.1 | mostly desperate |
 | [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-i1-GGUF/resolve/main/NoromaidxOpenGPT4-2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 12.8 |  |
 | [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-i1-GGUF/resolve/main/NoromaidxOpenGPT4-2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 14.2 |  |
 | [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-i1-GGUF/resolve/main/NoromaidxOpenGPT4-2.i1-IQ2_S.gguf) | i1-IQ2_S | 14.4 |  |
@@ -44,7 +44,7 @@ more details, including on how to concatenate multi-part files.
 | [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-i1-GGUF/resolve/main/NoromaidxOpenGPT4-2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 22.8 | IQ3_S probably better |
 | [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-i1-GGUF/resolve/main/NoromaidxOpenGPT4-2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 24.4 | IQ3_M probably better |
 | [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-i1-GGUF/resolve/main/NoromaidxOpenGPT4-2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 25.3 |  |
-| [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-i1-GGUF/resolve/main/NoromaidxOpenGPT4-2.i1-IQ4_NL.gguf) | i1-IQ4_NL | 26.8 | slightly worse than Q4_K_S |
+| [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-i1-GGUF/resolve/main/NoromaidxOpenGPT4-2.i1-IQ4_NL.gguf) | i1-IQ4_NL | 26.8 | prefer IQ4_XS |
 | [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-i1-GGUF/resolve/main/NoromaidxOpenGPT4-2.i1-Q4_0.gguf) | i1-Q4_0 | 26.8 | fast, low quality |
 | [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-i1-GGUF/resolve/main/NoromaidxOpenGPT4-2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 27.0 | optimal size/speed/quality |
 | [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-i1-GGUF/resolve/main/NoromaidxOpenGPT4-2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 28.7 | fast, recommended |
@@ -52,7 +52,6 @@ more details, including on how to concatenate multi-part files.
 | [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-i1-GGUF/resolve/main/NoromaidxOpenGPT4-2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 33.5 |  |
 | [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-i1-GGUF/resolve/main/NoromaidxOpenGPT4-2.i1-Q6_K.gguf) | i1-Q6_K | 38.6 | practically like static Q6_K |
 
-
 Here is a handy graph by ikawrakow comparing some lower-quality quant
 types (lower is better):