auto-patch README.md

README.md

@@ -35,12 +35,30 @@ more details, including on how to concatenate multi-part files.
 
 | Link | Type | Size/GB | Notes |
 |:-----|:-----|--------:|:------|
+| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 1.6 | for the desperate |
+| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 1.7 | mostly desperate |
+| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.9 |  |
+| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 2.2 |  |
+| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 2.4 |  |
 | [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-Q2_K.gguf) | i1-Q2_K | 2.7 | IQ3_XXS probably better |
 | [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.7 | lower quality |
+| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.0 |  |
+| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 3.0 | beats Q3_K* |
+| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.0 | IQ3_XS probably better |
 | [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 3.4 |  |
 | [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.6 | IQ3_S probably better |
+| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 3.7 |  |
+| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 3.9 | fast on arm, low quality |
+| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 3.9 | fast on arm+i8mm, low quality |
+| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 3.9 | fast on arm+sve, low quality |
+| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-Q4_0.gguf) | i1-Q4_0 | 3.9 | fast, low quality |
 | [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 3.9 | optimal size/speed/quality |
+| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.9 | IQ3_M probably better |
 | [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.4 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 4.7 |  |
+| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-Q6_K.gguf) | i1-Q6_K | 5.6 | practically like static Q6_K |
 
 Here is a handy graph by ikawrakow comparing some lower-quality quant
 types (lower is better):