mradermacher
/

koishi-8x7b-qlora-GGUF

Inference Endpoints

Model card Files Files and versions Community

mradermacher commited on Apr 23

Commit

c62593e

•

1 Parent(s): 89409bf

auto-patch README.md

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -30,6 +30,7 @@ more details, including on how to concatenate multi-part files.
 | Link | Type | Size/GB | Notes |
 |:-----|:-----|--------:|:------|
 | [GGUF](https://huggingface.co/mradermacher/koishi-8x7b-qlora-GGUF/resolve/main/koishi-8x7b-qlora.IQ3_S.gguf) | IQ3_S | 20.5 | beats Q3_K* |
 | [GGUF](https://huggingface.co/mradermacher/koishi-8x7b-qlora-GGUF/resolve/main/koishi-8x7b-qlora.Q8_0.gguf) | Q8_0 | 49.7 | fast, best quality |

 | Link | Type | Size/GB | Notes |
 |:-----|:-----|--------:|:------|
 | [GGUF](https://huggingface.co/mradermacher/koishi-8x7b-qlora-GGUF/resolve/main/koishi-8x7b-qlora.IQ3_S.gguf) | IQ3_S | 20.5 | beats Q3_K* |
+| [GGUF](https://huggingface.co/mradermacher/koishi-8x7b-qlora-GGUF/resolve/main/koishi-8x7b-qlora.Q4_K_S.gguf) | Q4_K_S | 26.8 | fast, recommended |
 | [GGUF](https://huggingface.co/mradermacher/koishi-8x7b-qlora-GGUF/resolve/main/koishi-8x7b-qlora.Q8_0.gguf) | Q8_0 | 49.7 | fast, best quality |