From f922e5e1747bf70e20f037d54ff19706db95ecc6 Mon Sep 17 00:00:00 2001 From: team mradermacher Date: Fri, 2 Jan 2026 08:28:57 +0000 Subject: [PATCH] auto-patch README.md --- README.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/README.md b/README.md index 2629ca7..92b2501 100644 --- a/README.md +++ b/README.md @@ -40,9 +40,13 @@ more details, including on how to concatenate multi-part files. | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/IQuest-Coder-V1-40B-Base-i1-GGUF/resolve/main/IQuest-Coder-V1-40B-Base.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/IQuest-Coder-V1-40B-Base-i1-GGUF/resolve/main/IQuest-Coder-V1-40B-Base.i1-IQ2_M.gguf) | i1-IQ2_M | 13.5 | | | [GGUF](https://huggingface.co/mradermacher/IQuest-Coder-V1-40B-Base-i1-GGUF/resolve/main/IQuest-Coder-V1-40B-Base.i1-Q2_K.gguf) | i1-Q2_K | 14.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/IQuest-Coder-V1-40B-Base-i1-GGUF/resolve/main/IQuest-Coder-V1-40B-Base.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 15.5 | lower quality | | [GGUF](https://huggingface.co/mradermacher/IQuest-Coder-V1-40B-Base-i1-GGUF/resolve/main/IQuest-Coder-V1-40B-Base.i1-IQ3_M.gguf) | i1-IQ3_M | 17.9 | | +| [GGUF](https://huggingface.co/mradermacher/IQuest-Coder-V1-40B-Base-i1-GGUF/resolve/main/IQuest-Coder-V1-40B-Base.i1-Q3_K_M.gguf) | i1-Q3_K_M | 19.3 | IQ3_S probably better | | [GGUF](https://huggingface.co/mradermacher/IQuest-Coder-V1-40B-Base-i1-GGUF/resolve/main/IQuest-Coder-V1-40B-Base.i1-Q4_K_S.gguf) | i1-Q4_K_S | 22.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/IQuest-Coder-V1-40B-Base-i1-GGUF/resolve/main/IQuest-Coder-V1-40B-Base.i1-Q4_K_M.gguf) | i1-Q4_K_M | 24.1 | fast, recommended | Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):