auto-patch README.md

README.md

@@ -39,6 +39,30 @@ more details, including on how to concatenate multi-part files.
 | Link | Type | Size/GB | Notes |
 |:-----|:-----|--------:|:------|
 | [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-i1-GGUF/resolve/main/Llama3.2-CULO-1B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-i1-GGUF/resolve/main/Llama3.2-CULO-1B.i1-IQ1_S.gguf) | i1-IQ1_S | 0.6 | for the desperate |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-i1-GGUF/resolve/main/Llama3.2-CULO-1B.i1-IQ1_M.gguf) | i1-IQ1_M | 0.6 | mostly desperate |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-i1-GGUF/resolve/main/Llama3.2-CULO-1B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.6 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-i1-GGUF/resolve/main/Llama3.2-CULO-1B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.7 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-i1-GGUF/resolve/main/Llama3.2-CULO-1B.i1-IQ2_S.gguf) | i1-IQ2_S | 0.7 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-i1-GGUF/resolve/main/Llama3.2-CULO-1B.i1-IQ2_M.gguf) | i1-IQ2_M | 0.7 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-i1-GGUF/resolve/main/Llama3.2-CULO-1B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.7 | very low quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-i1-GGUF/resolve/main/Llama3.2-CULO-1B.i1-Q2_K.gguf) | i1-Q2_K | 0.8 | IQ3_XXS probably better |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-i1-GGUF/resolve/main/Llama3.2-CULO-1B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.8 | lower quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-i1-GGUF/resolve/main/Llama3.2-CULO-1B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.8 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-i1-GGUF/resolve/main/Llama3.2-CULO-1B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.9 | IQ3_XS probably better |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-i1-GGUF/resolve/main/Llama3.2-CULO-1B.i1-IQ3_S.gguf) | i1-IQ3_S | 0.9 | beats Q3_K* |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-i1-GGUF/resolve/main/Llama3.2-CULO-1B.i1-IQ3_M.gguf) | i1-IQ3_M | 0.9 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-i1-GGUF/resolve/main/Llama3.2-CULO-1B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.9 | IQ3_S probably better |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-i1-GGUF/resolve/main/Llama3.2-CULO-1B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.9 | IQ3_M probably better |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-i1-GGUF/resolve/main/Llama3.2-CULO-1B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.0 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-i1-GGUF/resolve/main/Llama3.2-CULO-1B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 1.0 | prefer IQ4_XS |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-i1-GGUF/resolve/main/Llama3.2-CULO-1B.i1-Q4_0.gguf) | i1-Q4_0 | 1.0 | fast, low quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-i1-GGUF/resolve/main/Llama3.2-CULO-1B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.0 | optimal size/speed/quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-i1-GGUF/resolve/main/Llama3.2-CULO-1B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.1 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-i1-GGUF/resolve/main/Llama3.2-CULO-1B.i1-Q4_1.gguf) | i1-Q4_1 | 1.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-i1-GGUF/resolve/main/Llama3.2-CULO-1B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.2 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-i1-GGUF/resolve/main/Llama3.2-CULO-1B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.2 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-i1-GGUF/resolve/main/Llama3.2-CULO-1B.i1-Q6_K.gguf) | i1-Q6_K | 1.3 | practically like static Q6_K |
 
 Here is a handy graph by ikawrakow comparing some lower-quality quant
 types (lower is better):