auto-patch README.md

README.md

@@ -38,10 +38,27 @@ more details, including on how to concatenate multi-part files.
 
 | Link | Type | Size/GB | Notes |
 |:-----|:-----|--------:|:------|
+| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-2ex-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b-2ex.i1-IQ1_S.gguf) | i1-IQ1_S | 7.5 | for the desperate |
+| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-2ex-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b-2ex.i1-IQ1_M.gguf) | i1-IQ1_M | 8.3 | mostly desperate |
+| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-2ex-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b-2ex.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.6 |  |
+| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-2ex-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b-2ex.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.7 |  |
+| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-2ex-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b-2ex.i1-IQ2_S.gguf) | i1-IQ2_S | 11.0 |  |
+| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-2ex-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b-2ex.i1-IQ2_M.gguf) | i1-IQ2_M | 12.0 |  |
 | [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-2ex-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b-2ex.i1-Q2_K.gguf) | i1-Q2_K | 13.3 | IQ3_XXS probably better |
 | [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-2ex-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b-2ex.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 14.0 | lower quality |
+| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-2ex-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b-2ex.i1-IQ3_XS.gguf) | i1-IQ3_XS | 14.9 |  |
+| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-2ex-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b-2ex.i1-Q3_K_S.gguf) | i1-Q3_K_S | 15.7 | IQ3_XS probably better |
+| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-2ex-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b-2ex.i1-IQ3_S.gguf) | i1-IQ3_S | 15.7 | beats Q3_K* |
+| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-2ex-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b-2ex.i1-IQ3_M.gguf) | i1-IQ3_M | 16.0 |  |
 | [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-2ex-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b-2ex.i1-Q3_K_M.gguf) | i1-Q3_K_M | 17.4 | IQ3_S probably better |
+| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-2ex-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b-2ex.i1-Q3_K_L.gguf) | i1-Q3_K_L | 18.8 | IQ3_M probably better |
+| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-2ex-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b-2ex.i1-IQ4_XS.gguf) | i1-IQ4_XS | 19.4 |  |
+| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-2ex-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b-2ex.i1-Q4_0.gguf) | i1-Q4_0 | 20.5 | fast, low quality |
 | [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-2ex-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b-2ex.i1-Q4_K_S.gguf) | i1-Q4_K_S | 20.6 | optimal size/speed/quality |
+| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-2ex-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b-2ex.i1-Q4_K_M.gguf) | i1-Q4_K_M | 21.9 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-2ex-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b-2ex.i1-Q5_K_S.gguf) | i1-Q5_K_S | 24.9 |  |
+| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-2ex-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b-2ex.i1-Q5_K_M.gguf) | i1-Q5_K_M | 25.7 |  |
+| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-2ex-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b-2ex.i1-Q6_K.gguf) | i1-Q6_K | 29.7 | practically like static Q6_K |
 
 Here is a handy graph by ikawrakow comparing some lower-quality quant
 types (lower is better):