auto-patch README.md

README.md

@@ -13,7 +13,6 @@ tags:
 
 weighted/imatrix quants of https://huggingface.co/Undi95/LewdGem-40B
 
-
 <!-- provided-files -->
 static quants are available at https://huggingface.co/mradermacher/LewdGem-40B-GGUF
 ## Usage
@@ -29,6 +28,12 @@ more details, including on how to concatenate multi-part files.
 | Link | Type | Size/GB | Notes |
 |:-----|:-----|--------:|:------|
 | [GGUF](https://huggingface.co/mradermacher/LewdGem-40B-i1-GGUF/resolve/main/LewdGem-40B.i1-Q2_K.gguf) | i1-Q2_K | 14.4 | IQ3_XXS probably better |
+| [GGUF](https://huggingface.co/mradermacher/LewdGem-40B-i1-GGUF/resolve/main/LewdGem-40B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 16.9 | IQ3_XS probably better |
+| [GGUF](https://huggingface.co/mradermacher/LewdGem-40B-i1-GGUF/resolve/main/LewdGem-40B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 18.8 | IQ3_S probably better |
+| [GGUF](https://huggingface.co/mradermacher/LewdGem-40B-i1-GGUF/resolve/main/LewdGem-40B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 20.4 | IQ3_M probably better |
+| [GGUF](https://huggingface.co/mradermacher/LewdGem-40B-i1-GGUF/resolve/main/LewdGem-40B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 22.2 | optimal size/speed/quality |
+| [GGUF](https://huggingface.co/mradermacher/LewdGem-40B-i1-GGUF/resolve/main/LewdGem-40B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 23.6 | fast, medium quality |
+| [GGUF](https://huggingface.co/mradermacher/LewdGem-40B-i1-GGUF/resolve/main/LewdGem-40B.i1-Q6_K.gguf) | i1-Q6_K | 31.9 | practically like static Q6_K |
 
 
 Here is a handy graph by ikawrakow comparing some lower-quality quant