mradermacher/Cydonia-Redux-22B-v1.1-i1-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

auto-patch README.md

Browse Source
This commit is contained in:
team mradermacher
2025-10-13 05:27:52 +00:00
committed by system
parent ec192d356b
commit 6c41d02c3b
1 changed files with 9 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
README.md
View File

@@ -37,10 +37,19 @@ more details, including on how to concatenate multi-part files.
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Cydonia-Redux-22B-v1.1-i1-GGUF/resolve/main/Cydonia-Redux-22B-v1.1.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
| [GGUF](https://huggingface.co/mradermacher/Cydonia-Redux-22B-v1.1-i1-GGUF/resolve/main/Cydonia-Redux-22B-v1.1.i1-IQ1_M.gguf) | i1-IQ1_M | 5.4 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/Cydonia-Redux-22B-v1.1-i1-GGUF/resolve/main/Cydonia-Redux-22B-v1.1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 6.1 | |
| [GGUF](https://huggingface.co/mradermacher/Cydonia-Redux-22B-v1.1-i1-GGUF/resolve/main/Cydonia-Redux-22B-v1.1.i1-IQ2_M.gguf) | i1-IQ2_M | 7.7 | |
| [GGUF](https://huggingface.co/mradermacher/Cydonia-Redux-22B-v1.1-i1-GGUF/resolve/main/Cydonia-Redux-22B-v1.1.i1-Q2_K_S.gguf) | i1-Q2_K_S | 7.8 | very low quality |
| [GGUF](https://huggingface.co/mradermacher/Cydonia-Redux-22B-v1.1-i1-GGUF/resolve/main/Cydonia-Redux-22B-v1.1.i1-Q2_K.gguf) | i1-Q2_K | 8.4 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Cydonia-Redux-22B-v1.1-i1-GGUF/resolve/main/Cydonia-Redux-22B-v1.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 8.7 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Cydonia-Redux-22B-v1.1-i1-GGUF/resolve/main/Cydonia-Redux-22B-v1.1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 9.7 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Cydonia-Redux-22B-v1.1-i1-GGUF/resolve/main/Cydonia-Redux-22B-v1.1.i1-IQ3_M.gguf) | i1-IQ3_M | 10.2 | |
| [GGUF](https://huggingface.co/mradermacher/Cydonia-Redux-22B-v1.1-i1-GGUF/resolve/main/Cydonia-Redux-22B-v1.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 10.9 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/Cydonia-Redux-22B-v1.1-i1-GGUF/resolve/main/Cydonia-Redux-22B-v1.1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 12.0 | |
| [GGUF](https://huggingface.co/mradermacher/Cydonia-Redux-22B-v1.1-i1-GGUF/resolve/main/Cydonia-Redux-22B-v1.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 12.8 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/Cydonia-Redux-22B-v1.1-i1-GGUF/resolve/main/Cydonia-Redux-22B-v1.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 13.4 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Cydonia-Redux-22B-v1.1-i1-GGUF/resolve/main/Cydonia-Redux-22B-v1.1.i1-Q6_K.gguf) | i1-Q6_K | 18.4 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):