auto-patch README.md

README.md

@@ -45,6 +45,8 @@ more details, including on how to concatenate multi-part files.
 | [GGUF](https://huggingface.co/mradermacher/Llama-TI-8B-GGUF/resolve/main/Llama-TI-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 |  |
 | [GGUF](https://huggingface.co/mradermacher/Llama-TI-8B-GGUF/resolve/main/Llama-TI-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
 | [GGUF](https://huggingface.co/mradermacher/Llama-TI-8B-GGUF/resolve/main/Llama-TI-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-TI-8B-GGUF/resolve/main/Llama-TI-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-TI-8B-GGUF/resolve/main/Llama-TI-8B.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality |
 | [GGUF](https://huggingface.co/mradermacher/Llama-TI-8B-GGUF/resolve/main/Llama-TI-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
 | [GGUF](https://huggingface.co/mradermacher/Llama-TI-8B-GGUF/resolve/main/Llama-TI-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
 | [GGUF](https://huggingface.co/mradermacher/Llama-TI-8B-GGUF/resolve/main/Llama-TI-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 |  |