auto-patch README.md

README.md

@@ -35,16 +35,29 @@ more details, including on how to concatenate multi-part files.
 
 | Link | Type | Size/GB | Notes |
 |:-----|:-----|--------:|:------|
+| [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-COT-i1-GGUF/resolve/main/Llama3.3-70B-COT.i1-IQ1_S.gguf) | i1-IQ1_S | 3.5 | for the desperate |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-COT-i1-GGUF/resolve/main/Llama3.3-70B-COT.i1-IQ1_M.gguf) | i1-IQ1_M | 3.8 | mostly desperate |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-COT-i1-GGUF/resolve/main/Llama3.3-70B-COT.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.3 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-COT-i1-GGUF/resolve/main/Llama3.3-70B-COT.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.7 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-COT-i1-GGUF/resolve/main/Llama3.3-70B-COT.i1-IQ2_S.gguf) | i1-IQ2_S | 4.9 |  |
 | [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-COT-i1-GGUF/resolve/main/Llama3.3-70B-COT.i1-IQ2_M.gguf) | i1-IQ2_M | 5.3 |  |
 | [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-COT-i1-GGUF/resolve/main/Llama3.3-70B-COT.i1-Q2_K_S.gguf) | i1-Q2_K_S | 5.3 | very low quality |
 | [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-COT-i1-GGUF/resolve/main/Llama3.3-70B-COT.i1-Q2_K.gguf) | i1-Q2_K | 5.7 | IQ3_XXS probably better |
 | [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-COT-i1-GGUF/resolve/main/Llama3.3-70B-COT.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.9 | lower quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-COT-i1-GGUF/resolve/main/Llama3.3-70B-COT.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.3 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-COT-i1-GGUF/resolve/main/Llama3.3-70B-COT.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.6 | IQ3_XS probably better |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-COT-i1-GGUF/resolve/main/Llama3.3-70B-COT.i1-IQ3_S.gguf) | i1-IQ3_S | 6.6 | beats Q3_K* |
 | [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-COT-i1-GGUF/resolve/main/Llama3.3-70B-COT.i1-IQ3_M.gguf) | i1-IQ3_M | 6.8 |  |
 | [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-COT-i1-GGUF/resolve/main/Llama3.3-70B-COT.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.3 | IQ3_S probably better |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-COT-i1-GGUF/resolve/main/Llama3.3-70B-COT.i1-Q3_K_L.gguf) | i1-Q3_K_L | 7.9 | IQ3_M probably better |
 | [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-COT-i1-GGUF/resolve/main/Llama3.3-70B-COT.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-COT-i1-GGUF/resolve/main/Llama3.3-70B-COT.i1-Q4_0.gguf) | i1-Q4_0 | 8.5 | fast, low quality |
 | [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-COT-i1-GGUF/resolve/main/Llama3.3-70B-COT.i1-IQ4_NL.gguf) | i1-IQ4_NL | 8.5 | prefer IQ4_XS |
 | [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-COT-i1-GGUF/resolve/main/Llama3.3-70B-COT.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.5 | optimal size/speed/quality |
 | [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-COT-i1-GGUF/resolve/main/Llama3.3-70B-COT.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.0 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-COT-i1-GGUF/resolve/main/Llama3.3-70B-COT.i1-Q4_1.gguf) | i1-Q4_1 | 9.4 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-COT-i1-GGUF/resolve/main/Llama3.3-70B-COT.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.3 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-COT-i1-GGUF/resolve/main/Llama3.3-70B-COT.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.5 |  |
 | [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-COT-i1-GGUF/resolve/main/Llama3.3-70B-COT.i1-Q6_K.gguf) | i1-Q6_K | 12.1 | practically like static Q6_K |
 
 Here is a handy graph by ikawrakow comparing some lower-quality quant