diff --git a/README.md b/README.md index 2837e3c..41b41d5 100644 --- a/README.md +++ b/README.md @@ -44,6 +44,8 @@ more details, including on how to concatenate multi-part files. |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/Warlock-7B-v3-Uncensored-i1-GGUF/resolve/main/Warlock-7B-v3-Uncensored.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/Warlock-7B-v3-Uncensored-i1-GGUF/resolve/main/Warlock-7B-v3-Uncensored.i1-Q2_K.gguf) | i1-Q2_K | 2.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Warlock-7B-v3-Uncensored-i1-GGUF/resolve/main/Warlock-7B-v3-Uncensored.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Warlock-7B-v3-Uncensored-i1-GGUF/resolve/main/Warlock-7B-v3-Uncensored.i1-IQ3_M.gguf) | i1-IQ3_M | 3.4 | | Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):