auto-patch README.md

README.md

@@ -35,10 +35,15 @@ more details, including on how to concatenate multi-part files.
 | [GGUF](https://huggingface.co/mradermacher/mllama-3.1-8b-instruct-GGUF/resolve/main/mllama-3.1-8b-instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 |  |
 | [GGUF](https://huggingface.co/mradermacher/mllama-3.1-8b-instruct-GGUF/resolve/main/mllama-3.1-8b-instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
 | [GGUF](https://huggingface.co/mradermacher/mllama-3.1-8b-instruct-GGUF/resolve/main/mllama-3.1-8b-instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 |  |
+| [GGUF](https://huggingface.co/mradermacher/mllama-3.1-8b-instruct-GGUF/resolve/main/mllama-3.1-8b-instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 |  |
+| [GGUF](https://huggingface.co/mradermacher/mllama-3.1-8b-instruct-GGUF/resolve/main/mllama-3.1-8b-instruct.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality |
 | [GGUF](https://huggingface.co/mradermacher/mllama-3.1-8b-instruct-GGUF/resolve/main/mllama-3.1-8b-instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
 | [GGUF](https://huggingface.co/mradermacher/mllama-3.1-8b-instruct-GGUF/resolve/main/mllama-3.1-8b-instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/mllama-3.1-8b-instruct-GGUF/resolve/main/mllama-3.1-8b-instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 |  |
+| [GGUF](https://huggingface.co/mradermacher/mllama-3.1-8b-instruct-GGUF/resolve/main/mllama-3.1-8b-instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 |  |
 | [GGUF](https://huggingface.co/mradermacher/mllama-3.1-8b-instruct-GGUF/resolve/main/mllama-3.1-8b-instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
 | [GGUF](https://huggingface.co/mradermacher/mllama-3.1-8b-instruct-GGUF/resolve/main/mllama-3.1-8b-instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
+| [GGUF](https://huggingface.co/mradermacher/mllama-3.1-8b-instruct-GGUF/resolve/main/mllama-3.1-8b-instruct.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
 
 Here is a handy graph by ikawrakow comparing some lower-quality quant
 types (lower is better):