auto-patch README.md

README.md

@@ -36,10 +36,14 @@ more details, including on how to concatenate multi-part files.
 | [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-gemma-2-9B-GGUF/resolve/main/MT5-Gen5-gemma-2-9B.Q3_K_S.gguf) | Q3_K_S | 4.4 |  |
 | [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-gemma-2-9B-GGUF/resolve/main/MT5-Gen5-gemma-2-9B.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality |
 | [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-gemma-2-9B-GGUF/resolve/main/MT5-Gen5-gemma-2-9B.Q3_K_L.gguf) | Q3_K_L | 5.2 |  |
+| [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-gemma-2-9B-GGUF/resolve/main/MT5-Gen5-gemma-2-9B.IQ4_XS.gguf) | IQ4_XS | 5.3 |  |
 | [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-gemma-2-9B-GGUF/resolve/main/MT5-Gen5-gemma-2-9B.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended |
 | [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-gemma-2-9B-GGUF/resolve/main/MT5-Gen5-gemma-2-9B.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-gemma-2-9B-GGUF/resolve/main/MT5-Gen5-gemma-2-9B.Q5_K_S.gguf) | Q5_K_S | 6.6 |  |
+| [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-gemma-2-9B-GGUF/resolve/main/MT5-Gen5-gemma-2-9B.Q5_K_M.gguf) | Q5_K_M | 6.7 |  |
 | [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-gemma-2-9B-GGUF/resolve/main/MT5-Gen5-gemma-2-9B.Q6_K.gguf) | Q6_K | 7.7 | very good quality |
 | [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-gemma-2-9B-GGUF/resolve/main/MT5-Gen5-gemma-2-9B.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality |
+| [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-gemma-2-9B-GGUF/resolve/main/MT5-Gen5-gemma-2-9B.f16.gguf) | f16 | 18.6 | 16 bpw, overkill |
 
 Here is a handy graph by ikawrakow comparing some lower-quality quant
 types (lower is better):