Hugging Face's logo

mradermacher
/
X-ALMA-13B-Group5-GGUF

Transformers
GGUF
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
bca5e17
·
verified ·
1 Parent(s): e893d44

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -42,8 +42,13 @@ more details, including on how to concatenate multi-part files.
42
  | [GGUF](https://huggingface.co/mradermacher/X-ALMA-13B-Group5-GGUF/resolve/main/X-ALMA-13B-Group5.Q3_K_S.gguf) | Q3_K_S | 5.8 | |
43
  | [GGUF](https://huggingface.co/mradermacher/X-ALMA-13B-Group5-GGUF/resolve/main/X-ALMA-13B-Group5.Q3_K_M.gguf) | Q3_K_M | 6.4 | lower quality |
44
  | [GGUF](https://huggingface.co/mradermacher/X-ALMA-13B-Group5-GGUF/resolve/main/X-ALMA-13B-Group5.Q3_K_L.gguf) | Q3_K_L | 7.0 | |
 
45
  | [GGUF](https://huggingface.co/mradermacher/X-ALMA-13B-Group5-GGUF/resolve/main/X-ALMA-13B-Group5.Q4_K_S.gguf) | Q4_K_S | 7.5 | fast, recommended |
 
 
 
46
  | [GGUF](https://huggingface.co/mradermacher/X-ALMA-13B-Group5-GGUF/resolve/main/X-ALMA-13B-Group5.Q6_K.gguf) | Q6_K | 10.8 | very good quality |
 
47
 
48
  Here is a handy graph by ikawrakow comparing some lower-quality quant
49
  types (lower is better):
 
42
  | [GGUF](https://huggingface.co/mradermacher/X-ALMA-13B-Group5-GGUF/resolve/main/X-ALMA-13B-Group5.Q3_K_S.gguf) | Q3_K_S | 5.8 | |
43
  | [GGUF](https://huggingface.co/mradermacher/X-ALMA-13B-Group5-GGUF/resolve/main/X-ALMA-13B-Group5.Q3_K_M.gguf) | Q3_K_M | 6.4 | lower quality |
44
  | [GGUF](https://huggingface.co/mradermacher/X-ALMA-13B-Group5-GGUF/resolve/main/X-ALMA-13B-Group5.Q3_K_L.gguf) | Q3_K_L | 7.0 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/X-ALMA-13B-Group5-GGUF/resolve/main/X-ALMA-13B-Group5.IQ4_XS.gguf) | IQ4_XS | 7.1 | |
46
  | [GGUF](https://huggingface.co/mradermacher/X-ALMA-13B-Group5-GGUF/resolve/main/X-ALMA-13B-Group5.Q4_K_S.gguf) | Q4_K_S | 7.5 | fast, recommended |
47
+ | [GGUF](https://huggingface.co/mradermacher/X-ALMA-13B-Group5-GGUF/resolve/main/X-ALMA-13B-Group5.Q4_K_M.gguf) | Q4_K_M | 8.0 | fast, recommended |
48
+ | [GGUF](https://huggingface.co/mradermacher/X-ALMA-13B-Group5-GGUF/resolve/main/X-ALMA-13B-Group5.Q5_K_S.gguf) | Q5_K_S | 9.1 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/X-ALMA-13B-Group5-GGUF/resolve/main/X-ALMA-13B-Group5.Q5_K_M.gguf) | Q5_K_M | 9.3 | |
50
  | [GGUF](https://huggingface.co/mradermacher/X-ALMA-13B-Group5-GGUF/resolve/main/X-ALMA-13B-Group5.Q6_K.gguf) | Q6_K | 10.8 | very good quality |
51
+ | [GGUF](https://huggingface.co/mradermacher/X-ALMA-13B-Group5-GGUF/resolve/main/X-ALMA-13B-Group5.Q8_0.gguf) | Q8_0 | 13.9 | fast, best quality |
52
 
53
  Here is a handy graph by ikawrakow comparing some lower-quality quant
54
  types (lower is better):