auto-patch README.md

README.md

@@ -28,7 +28,27 @@ more details, including on how to concatenate multi-part files.
 
 | Link | Type | Size/GB | Notes |
 |:-----|:-----|--------:|:------|
+| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-70B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-70B-Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 15.4 | for the desperate |
+| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-70B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-70B-Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 16.9 | mostly desperate |
+| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-70B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-70B-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 19.2 |  |
+| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-70B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-70B-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 21.2 |  |
+| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-70B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-70B-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 22.3 |  |
+| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-70B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-70B-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 24.2 |  |
 | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-70B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-70B-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 26.5 | IQ3_XXS probably better |
+| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-70B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-70B-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 27.6 | lower quality |
+| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-70B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-70B-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 29.4 |  |
+| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-70B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-70B-Instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 31.0 | beats Q3_K* |
+| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-70B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-70B-Instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 31.0 | IQ3_XS probably better |
+| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-70B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-70B-Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 32.0 |  |
+| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-70B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-70B-Instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 34.4 | IQ3_S probably better |
+| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-70B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-70B-Instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 37.2 | IQ3_M probably better |
+| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-70B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-70B-Instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 38.0 |  |
+| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-70B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-70B-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 40.2 | fast, low quality |
+| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-70B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-70B-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 40.4 | optimal size/speed/quality |
+| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-70B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-70B-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 42.6 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-70B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-70B-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 48.8 |  |
+| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-70B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-70B-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 50.0 |  |
+| [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3.1-70B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-70B-Instruct.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3.1-70B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-70B-Instruct.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 58.0 | practically like static Q6_K |
 
 Here is a handy graph by ikawrakow comparing some lower-quality quant
 types (lower is better):