Upload README.md with huggingface_hub

README.md

@@ -31,6 +31,8 @@ more details, including on how to concatenate multi-part files.
 | [GGUF](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q2_K.gguf) | Q2_K | 38.2 |  |
 | [GGUF](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.IQ3_XS.gguf) | IQ3_XS | 42.4 |  |
 | [GGUF](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q3_K_S.gguf) | Q3_K_S | 44.8 |  |
+| [GGUF](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.IQ3_S.gguf) | IQ3_S | 44.9 | fast, beats Q3_K* |
+| [GGUF](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.IQ3_M.gguf) | IQ3_M | 46.4 |  |
 | [PART 1](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q3_K_M.gguf.part2of2) | Q3_K_M | 49.9 | lower quality |
 | [PART 1](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q3_K_L.gguf.part2of2) | Q3_K_L | 54.4 |  |
 | [PART 1](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q4_K_S.gguf.part2of2) | Q4_K_S | 58.9 | fast, medium quality |
@@ -46,4 +48,7 @@ types (lower is better):
 
 ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
 
+And here are Artefact2's thoughts on the matter:
+https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
+
 <!-- end -->