auto-patch README.md

README.md

@@ -31,13 +31,22 @@ more details, including on how to concatenate multi-part files.
 
 | Link | Type | Size/GB | Notes |
 |:-----|:-----|--------:|:------|
+| [GGUF](https://huggingface.co/mradermacher/Mag-Mell-R1-21B-i1-GGUF/resolve/main/Mag-Mell-R1-21B.i1-IQ1_M.gguf) | i1-IQ1_M | 5.2 | mostly desperate |
+| [GGUF](https://huggingface.co/mradermacher/Mag-Mell-R1-21B-i1-GGUF/resolve/main/Mag-Mell-R1-21B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 5.9 |  |
+| [GGUF](https://huggingface.co/mradermacher/Mag-Mell-R1-21B-i1-GGUF/resolve/main/Mag-Mell-R1-21B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 6.4 |  |
 | [GGUF](https://huggingface.co/mradermacher/Mag-Mell-R1-21B-i1-GGUF/resolve/main/Mag-Mell-R1-21B.i1-IQ2_M.gguf) | i1-IQ2_M | 7.3 |  |
+| [GGUF](https://huggingface.co/mradermacher/Mag-Mell-R1-21B-i1-GGUF/resolve/main/Mag-Mell-R1-21B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 7.4 | very low quality |
 | [GGUF](https://huggingface.co/mradermacher/Mag-Mell-R1-21B-i1-GGUF/resolve/main/Mag-Mell-R1-21B.i1-Q2_K.gguf) | i1-Q2_K | 7.9 | IQ3_XXS probably better |
 | [GGUF](https://huggingface.co/mradermacher/Mag-Mell-R1-21B-i1-GGUF/resolve/main/Mag-Mell-R1-21B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 8.2 | lower quality |
+| [GGUF](https://huggingface.co/mradermacher/Mag-Mell-R1-21B-i1-GGUF/resolve/main/Mag-Mell-R1-21B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 9.1 | IQ3_XS probably better |
 | [GGUF](https://huggingface.co/mradermacher/Mag-Mell-R1-21B-i1-GGUF/resolve/main/Mag-Mell-R1-21B.i1-IQ3_M.gguf) | i1-IQ3_M | 9.5 |  |
 | [GGUF](https://huggingface.co/mradermacher/Mag-Mell-R1-21B-i1-GGUF/resolve/main/Mag-Mell-R1-21B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 10.1 | IQ3_S probably better |
+| [GGUF](https://huggingface.co/mradermacher/Mag-Mell-R1-21B-i1-GGUF/resolve/main/Mag-Mell-R1-21B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 10.9 | IQ3_M probably better |
+| [GGUF](https://huggingface.co/mradermacher/Mag-Mell-R1-21B-i1-GGUF/resolve/main/Mag-Mell-R1-21B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 11.2 |  |
 | [GGUF](https://huggingface.co/mradermacher/Mag-Mell-R1-21B-i1-GGUF/resolve/main/Mag-Mell-R1-21B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 11.8 | optimal size/speed/quality |
 | [GGUF](https://huggingface.co/mradermacher/Mag-Mell-R1-21B-i1-GGUF/resolve/main/Mag-Mell-R1-21B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 12.5 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Mag-Mell-R1-21B-i1-GGUF/resolve/main/Mag-Mell-R1-21B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 14.2 |  |
+| [GGUF](https://huggingface.co/mradermacher/Mag-Mell-R1-21B-i1-GGUF/resolve/main/Mag-Mell-R1-21B.i1-Q6_K.gguf) | i1-Q6_K | 16.9 | practically like static Q6_K |
 
 Here is a handy graph by ikawrakow comparing some lower-quality quant
 types (lower is better):