Hugging Face's logo

matrixportal
/
X-Ray_Alpha-GGUF

GGUF
English
llama-cpp
matrixportal
conversational
Model card Files Community
matrixportal commited on
Commit
9efe274
·
verified ·
1 Parent(s): 704ce63

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -37,4 +37,4 @@ Refer to the [original model card](https://huggingface.co/SicariusSicariiStuff/X
37
  | [Download](https://huggingface.co/matrixportal/X-Ray_Alpha-GGUF/resolve/main/x-ray_alpha-q8_0.gguf) | ![Q8_0](https://img.shields.io/badge/Q8_0-EA4335) ⚡ | Fast, best quality |
38
  | [Download](https://huggingface.co/matrixportal/X-Ray_Alpha-GGUF/resolve/main/x-ray_alpha-f16.gguf) | ![F16](https://img.shields.io/badge/F16-000000) | Maximum accuracy |
39
 
40
- 💡 **Tip:** Use `F16` for maximum precision when quality is critical
 
37
  | [Download](https://huggingface.co/matrixportal/X-Ray_Alpha-GGUF/resolve/main/x-ray_alpha-q8_0.gguf) | ![Q8_0](https://img.shields.io/badge/Q8_0-EA4335) ⚡ | Fast, best quality |
38
  | [Download](https://huggingface.co/matrixportal/X-Ray_Alpha-GGUF/resolve/main/x-ray_alpha-f16.gguf) | ![F16](https://img.shields.io/badge/F16-000000) | Maximum accuracy |
39
 
40
+ 💡 **Pro Tip:** Start with `Q4_K_M` for most use cases, only use `F16` if you need maximum precision.