auto-patch README.md

README.md

@@ -40,6 +40,10 @@ more details, including on how to concatenate multi-part files.
 |:-----|:-----|--------:|:------|
 | [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-480B-A35B-Instruct-i1-GGUF/resolve/main/Qwen3-Coder-480B-A35B-Instruct.imatrix.gguf) | imatrix | 0.7 | imatrix file (for creating your own qwuants) |
 | [PART 1](https://huggingface.co/mradermacher/Qwen3-Coder-480B-A35B-Instruct-i1-GGUF/resolve/main/Qwen3-Coder-480B-A35B-Instruct.i1-Q2_K.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Qwen3-Coder-480B-A35B-Instruct-i1-GGUF/resolve/main/Qwen3-Coder-480B-A35B-Instruct.i1-Q2_K.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Qwen3-Coder-480B-A35B-Instruct-i1-GGUF/resolve/main/Qwen3-Coder-480B-A35B-Instruct.i1-Q2_K.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Qwen3-Coder-480B-A35B-Instruct-i1-GGUF/resolve/main/Qwen3-Coder-480B-A35B-Instruct.i1-Q2_K.gguf.part4of4) | i1-Q2_K | 174.8 | IQ3_XXS probably better |
+| [PART 1](https://huggingface.co/mradermacher/Qwen3-Coder-480B-A35B-Instruct-i1-GGUF/resolve/main/Qwen3-Coder-480B-A35B-Instruct.i1-IQ3_XXS.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Qwen3-Coder-480B-A35B-Instruct-i1-GGUF/resolve/main/Qwen3-Coder-480B-A35B-Instruct.i1-IQ3_XXS.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Qwen3-Coder-480B-A35B-Instruct-i1-GGUF/resolve/main/Qwen3-Coder-480B-A35B-Instruct.i1-IQ3_XXS.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Qwen3-Coder-480B-A35B-Instruct-i1-GGUF/resolve/main/Qwen3-Coder-480B-A35B-Instruct.i1-IQ3_XXS.gguf.part4of4) | i1-IQ3_XXS | 184.4 | lower quality |
+| [P1](https://huggingface.co/mradermacher/Qwen3-Coder-480B-A35B-Instruct-i1-GGUF/resolve/main/Qwen3-Coder-480B-A35B-Instruct.i1-IQ3_M.gguf.part1of5) [P2](https://huggingface.co/mradermacher/Qwen3-Coder-480B-A35B-Instruct-i1-GGUF/resolve/main/Qwen3-Coder-480B-A35B-Instruct.i1-IQ3_M.gguf.part2of5) [P3](https://huggingface.co/mradermacher/Qwen3-Coder-480B-A35B-Instruct-i1-GGUF/resolve/main/Qwen3-Coder-480B-A35B-Instruct.i1-IQ3_M.gguf.part3of5) [P4](https://huggingface.co/mradermacher/Qwen3-Coder-480B-A35B-Instruct-i1-GGUF/resolve/main/Qwen3-Coder-480B-A35B-Instruct.i1-IQ3_M.gguf.part4of5) [P5](https://huggingface.co/mradermacher/Qwen3-Coder-480B-A35B-Instruct-i1-GGUF/resolve/main/Qwen3-Coder-480B-A35B-Instruct.i1-IQ3_M.gguf.part5of5) | i1-IQ3_M | 210.0 |  |
+| [P1](https://huggingface.co/mradermacher/Qwen3-Coder-480B-A35B-Instruct-i1-GGUF/resolve/main/Qwen3-Coder-480B-A35B-Instruct.i1-Q3_K_M.gguf.part1of5) [P2](https://huggingface.co/mradermacher/Qwen3-Coder-480B-A35B-Instruct-i1-GGUF/resolve/main/Qwen3-Coder-480B-A35B-Instruct.i1-Q3_K_M.gguf.part2of5) [P3](https://huggingface.co/mradermacher/Qwen3-Coder-480B-A35B-Instruct-i1-GGUF/resolve/main/Qwen3-Coder-480B-A35B-Instruct.i1-Q3_K_M.gguf.part3of5) [P4](https://huggingface.co/mradermacher/Qwen3-Coder-480B-A35B-Instruct-i1-GGUF/resolve/main/Qwen3-Coder-480B-A35B-Instruct.i1-Q3_K_M.gguf.part4of5) [P5](https://huggingface.co/mradermacher/Qwen3-Coder-480B-A35B-Instruct-i1-GGUF/resolve/main/Qwen3-Coder-480B-A35B-Instruct.i1-Q3_K_M.gguf.part5of5) | i1-Q3_K_M | 229.3 | IQ3_S probably better |
+| [P1](https://huggingface.co/mradermacher/Qwen3-Coder-480B-A35B-Instruct-i1-GGUF/resolve/main/Qwen3-Coder-480B-A35B-Instruct.i1-Q4_K_S.gguf.part1of6) [P2](https://huggingface.co/mradermacher/Qwen3-Coder-480B-A35B-Instruct-i1-GGUF/resolve/main/Qwen3-Coder-480B-A35B-Instruct.i1-Q4_K_S.gguf.part2of6) [P3](https://huggingface.co/mradermacher/Qwen3-Coder-480B-A35B-Instruct-i1-GGUF/resolve/main/Qwen3-Coder-480B-A35B-Instruct.i1-Q4_K_S.gguf.part3of6) [P4](https://huggingface.co/mradermacher/Qwen3-Coder-480B-A35B-Instruct-i1-GGUF/resolve/main/Qwen3-Coder-480B-A35B-Instruct.i1-Q4_K_S.gguf.part4of6) [P5](https://huggingface.co/mradermacher/Qwen3-Coder-480B-A35B-Instruct-i1-GGUF/resolve/main/Qwen3-Coder-480B-A35B-Instruct.i1-Q4_K_S.gguf.part5of6) [P6](https://huggingface.co/mradermacher/Qwen3-Coder-480B-A35B-Instruct-i1-GGUF/resolve/main/Qwen3-Coder-480B-A35B-Instruct.i1-Q4_K_S.gguf.part6of6) | i1-Q4_K_S | 272.9 | optimal size/speed/quality |
 
 Here is a handy graph by ikawrakow comparing some lower-quality quant
 types (lower is better):