diff --git a/README.md b/README.md index 464bbb4..9efe6d7 100644 --- a/README.md +++ b/README.md @@ -46,6 +46,16 @@ more details, including on how to concatenate multi-part files. | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/Gemma-3-27B-Derestricted-i1-GGUF/resolve/main/Gemma-3-27B-Derestricted.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-27B-Derestricted-i1-GGUF/resolve/main/Gemma-3-27B-Derestricted.i1-IQ2_M.gguf) | i1-IQ2_M | 9.6 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-27B-Derestricted-i1-GGUF/resolve/main/Gemma-3-27B-Derestricted.i1-Q2_K_S.gguf) | i1-Q2_K_S | 9.9 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-27B-Derestricted-i1-GGUF/resolve/main/Gemma-3-27B-Derestricted.i1-Q2_K.gguf) | i1-Q2_K | 10.6 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-27B-Derestricted-i1-GGUF/resolve/main/Gemma-3-27B-Derestricted.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 10.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-27B-Derestricted-i1-GGUF/resolve/main/Gemma-3-27B-Derestricted.i1-IQ3_M.gguf) | i1-IQ3_M | 12.6 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-27B-Derestricted-i1-GGUF/resolve/main/Gemma-3-27B-Derestricted.i1-Q3_K_M.gguf) | i1-Q3_K_M | 13.5 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-27B-Derestricted-i1-GGUF/resolve/main/Gemma-3-27B-Derestricted.i1-IQ4_XS.gguf) | i1-IQ4_XS | 14.9 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-27B-Derestricted-i1-GGUF/resolve/main/Gemma-3-27B-Derestricted.i1-Q4_K_S.gguf) | i1-Q4_K_S | 15.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-27B-Derestricted-i1-GGUF/resolve/main/Gemma-3-27B-Derestricted.i1-Q4_K_M.gguf) | i1-Q4_K_M | 16.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-27B-Derestricted-i1-GGUF/resolve/main/Gemma-3-27B-Derestricted.i1-Q6_K.gguf) | i1-Q6_K | 22.3 | practically like static Q6_K | Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):