auto-patch README.md

README.md

@@ -47,10 +47,14 @@ more details, including on how to concatenate multi-part files.
 | [GGUF](https://huggingface.co/mradermacher/Glm4-9B-RP-brb-GGUF/resolve/main/Glm4-9B-RP-brb.Q3_K_S.gguf) | Q3_K_S | 4.7 |  |
 | [GGUF](https://huggingface.co/mradermacher/Glm4-9B-RP-brb-GGUF/resolve/main/Glm4-9B-RP-brb.Q3_K_M.gguf) | Q3_K_M | 5.1 | lower quality |
 | [GGUF](https://huggingface.co/mradermacher/Glm4-9B-RP-brb-GGUF/resolve/main/Glm4-9B-RP-brb.Q3_K_L.gguf) | Q3_K_L | 5.3 |  |
+| [GGUF](https://huggingface.co/mradermacher/Glm4-9B-RP-brb-GGUF/resolve/main/Glm4-9B-RP-brb.IQ4_XS.gguf) | IQ4_XS | 5.4 |  |
 | [GGUF](https://huggingface.co/mradermacher/Glm4-9B-RP-brb-GGUF/resolve/main/Glm4-9B-RP-brb.Q4_K_S.gguf) | Q4_K_S | 5.9 | fast, recommended |
 | [GGUF](https://huggingface.co/mradermacher/Glm4-9B-RP-brb-GGUF/resolve/main/Glm4-9B-RP-brb.Q4_K_M.gguf) | Q4_K_M | 6.3 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Glm4-9B-RP-brb-GGUF/resolve/main/Glm4-9B-RP-brb.Q5_K_S.gguf) | Q5_K_S | 6.8 |  |
+| [GGUF](https://huggingface.co/mradermacher/Glm4-9B-RP-brb-GGUF/resolve/main/Glm4-9B-RP-brb.Q5_K_M.gguf) | Q5_K_M | 7.1 |  |
 | [GGUF](https://huggingface.co/mradermacher/Glm4-9B-RP-brb-GGUF/resolve/main/Glm4-9B-RP-brb.Q6_K.gguf) | Q6_K | 8.4 | very good quality |
 | [GGUF](https://huggingface.co/mradermacher/Glm4-9B-RP-brb-GGUF/resolve/main/Glm4-9B-RP-brb.Q8_0.gguf) | Q8_0 | 10.1 | fast, best quality |
+| [GGUF](https://huggingface.co/mradermacher/Glm4-9B-RP-brb-GGUF/resolve/main/Glm4-9B-RP-brb.f16.gguf) | f16 | 18.9 | 16 bpw, overkill |
 
 Here is a handy graph by ikawrakow comparing some lower-quality quant
 types (lower is better):