auto-patch README.md

README.md

@@ -179,7 +179,6 @@ tags:
 <!-- ### vocab_type:  -->
 static quants of https://huggingface.co/NousResearch/Meta-Llama-3-70B
 
-
 <!-- provided-files -->
 weighted/imatrix quants are available at https://huggingface.co/mradermacher/Meta-Llama-3-70B-i1-GGUF
 ## Usage
@@ -201,6 +200,7 @@ more details, including on how to concatenate multi-part files.
 | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-GGUF/resolve/main/Meta-Llama-3-70B.IQ3_M.gguf) | IQ3_M | 32.0 |  |
 | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-GGUF/resolve/main/Meta-Llama-3-70B.Q3_K_M.gguf) | Q3_K_M | 34.4 | lower quality |
 | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-GGUF/resolve/main/Meta-Llama-3-70B.Q3_K_L.gguf) | Q3_K_L | 37.2 |  |
+| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-GGUF/resolve/main/Meta-Llama-3-70B.IQ4_XS.gguf) | IQ4_XS | 38.4 |  |
 | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-GGUF/resolve/main/Meta-Llama-3-70B.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
 | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-GGUF/resolve/main/Meta-Llama-3-70B.Q4_K_M.gguf) | Q4_K_M | 42.6 | fast, recommended |
 | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-GGUF/resolve/main/Meta-Llama-3-70B.Q5_K_S.gguf) | Q5_K_S | 48.8 |  |