auto-patch README.md

README.md

@@ -31,12 +31,27 @@ more details, including on how to concatenate multi-part files.
 
 | Link | Type | Size/GB | Notes |
 |:-----|:-----|--------:|:------|
+| [GGUF](https://huggingface.co/mradermacher/Phind-CodeLlama-34B-v1-i1-GGUF/resolve/main/Phind-CodeLlama-34B-v1.i1-IQ1_S.gguf) | i1-IQ1_S | 7.4 | for the desperate |
+| [GGUF](https://huggingface.co/mradermacher/Phind-CodeLlama-34B-v1-i1-GGUF/resolve/main/Phind-CodeLlama-34B-v1.i1-IQ1_M.gguf) | i1-IQ1_M | 8.0 | mostly desperate |
+| [GGUF](https://huggingface.co/mradermacher/Phind-CodeLlama-34B-v1-i1-GGUF/resolve/main/Phind-CodeLlama-34B-v1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/Phind-CodeLlama-34B-v1-i1-GGUF/resolve/main/Phind-CodeLlama-34B-v1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/Phind-CodeLlama-34B-v1-i1-GGUF/resolve/main/Phind-CodeLlama-34B-v1.i1-IQ2_S.gguf) | i1-IQ2_S | 10.7 |  |
+| [GGUF](https://huggingface.co/mradermacher/Phind-CodeLlama-34B-v1-i1-GGUF/resolve/main/Phind-CodeLlama-34B-v1.i1-IQ2_M.gguf) | i1-IQ2_M | 11.6 |  |
 | [GGUF](https://huggingface.co/mradermacher/Phind-CodeLlama-34B-v1-i1-GGUF/resolve/main/Phind-CodeLlama-34B-v1.i1-Q2_K.gguf) | i1-Q2_K | 12.6 | IQ3_XXS probably better |
 | [GGUF](https://huggingface.co/mradermacher/Phind-CodeLlama-34B-v1-i1-GGUF/resolve/main/Phind-CodeLlama-34B-v1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 13.1 | lower quality |
+| [GGUF](https://huggingface.co/mradermacher/Phind-CodeLlama-34B-v1-i1-GGUF/resolve/main/Phind-CodeLlama-34B-v1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 14.0 |  |
+| [GGUF](https://huggingface.co/mradermacher/Phind-CodeLlama-34B-v1-i1-GGUF/resolve/main/Phind-CodeLlama-34B-v1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.7 | IQ3_XS probably better |
+| [GGUF](https://huggingface.co/mradermacher/Phind-CodeLlama-34B-v1-i1-GGUF/resolve/main/Phind-CodeLlama-34B-v1.i1-IQ3_S.gguf) | i1-IQ3_S | 14.8 | beats Q3_K* |
 | [GGUF](https://huggingface.co/mradermacher/Phind-CodeLlama-34B-v1-i1-GGUF/resolve/main/Phind-CodeLlama-34B-v1.i1-IQ3_M.gguf) | i1-IQ3_M | 15.3 |  |
 | [GGUF](https://huggingface.co/mradermacher/Phind-CodeLlama-34B-v1-i1-GGUF/resolve/main/Phind-CodeLlama-34B-v1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.4 | IQ3_S probably better |
+| [GGUF](https://huggingface.co/mradermacher/Phind-CodeLlama-34B-v1-i1-GGUF/resolve/main/Phind-CodeLlama-34B-v1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.9 | IQ3_M probably better |
+| [GGUF](https://huggingface.co/mradermacher/Phind-CodeLlama-34B-v1-i1-GGUF/resolve/main/Phind-CodeLlama-34B-v1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 18.2 |  |
+| [GGUF](https://huggingface.co/mradermacher/Phind-CodeLlama-34B-v1-i1-GGUF/resolve/main/Phind-CodeLlama-34B-v1.i1-Q4_0.gguf) | i1-Q4_0 | 19.2 | fast, low quality |
 | [GGUF](https://huggingface.co/mradermacher/Phind-CodeLlama-34B-v1-i1-GGUF/resolve/main/Phind-CodeLlama-34B-v1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 19.3 | optimal size/speed/quality |
 | [GGUF](https://huggingface.co/mradermacher/Phind-CodeLlama-34B-v1-i1-GGUF/resolve/main/Phind-CodeLlama-34B-v1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.3 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Phind-CodeLlama-34B-v1-i1-GGUF/resolve/main/Phind-CodeLlama-34B-v1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 23.3 |  |
+| [GGUF](https://huggingface.co/mradermacher/Phind-CodeLlama-34B-v1-i1-GGUF/resolve/main/Phind-CodeLlama-34B-v1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.9 |  |
+| [GGUF](https://huggingface.co/mradermacher/Phind-CodeLlama-34B-v1-i1-GGUF/resolve/main/Phind-CodeLlama-34B-v1.i1-Q6_K.gguf) | i1-Q6_K | 27.8 | practically like static Q6_K |
 
 Here is a handy graph by ikawrakow comparing some lower-quality quant
 types (lower is better):