Hugging Face's logo

mradermacher
/
GALAXY-16B-v1.0-GGUF

Transformers
GGUF
English
Not-For-All-Audiences
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
f09a39a
•
1 Parent(s): acc6bb7

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -41,9 +41,13 @@ more details, including on how to concatenate multi-part files.
41
  | [GGUF](https://huggingface.co/mradermacher/GALAXY-16B-v1.0-GGUF/resolve/main/GALAXY-16B-v1.0.Q3_K_S.gguf) | Q3_K_S | 7.0 | |
42
  | [GGUF](https://huggingface.co/mradermacher/GALAXY-16B-v1.0-GGUF/resolve/main/GALAXY-16B-v1.0.Q3_K_M.gguf) | Q3_K_M | 7.8 | lower quality |
43
  | [GGUF](https://huggingface.co/mradermacher/GALAXY-16B-v1.0-GGUF/resolve/main/GALAXY-16B-v1.0.Q3_K_L.gguf) | Q3_K_L | 8.5 | |
 
44
  | [GGUF](https://huggingface.co/mradermacher/GALAXY-16B-v1.0-GGUF/resolve/main/GALAXY-16B-v1.0.Q4_K_S.gguf) | Q4_K_S | 9.2 | fast, recommended |
45
  | [GGUF](https://huggingface.co/mradermacher/GALAXY-16B-v1.0-GGUF/resolve/main/GALAXY-16B-v1.0.Q4_K_M.gguf) | Q4_K_M | 9.7 | fast, recommended |
 
 
46
  | [GGUF](https://huggingface.co/mradermacher/GALAXY-16B-v1.0-GGUF/resolve/main/GALAXY-16B-v1.0.Q6_K.gguf) | Q6_K | 13.2 | very good quality |
 
47
 
48
  Here is a handy graph by ikawrakow comparing some lower-quality quant
49
  types (lower is better):
 
41
  | [GGUF](https://huggingface.co/mradermacher/GALAXY-16B-v1.0-GGUF/resolve/main/GALAXY-16B-v1.0.Q3_K_S.gguf) | Q3_K_S | 7.0 | |
42
  | [GGUF](https://huggingface.co/mradermacher/GALAXY-16B-v1.0-GGUF/resolve/main/GALAXY-16B-v1.0.Q3_K_M.gguf) | Q3_K_M | 7.8 | lower quality |
43
  | [GGUF](https://huggingface.co/mradermacher/GALAXY-16B-v1.0-GGUF/resolve/main/GALAXY-16B-v1.0.Q3_K_L.gguf) | Q3_K_L | 8.5 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/GALAXY-16B-v1.0-GGUF/resolve/main/GALAXY-16B-v1.0.IQ4_XS.gguf) | IQ4_XS | 8.8 | |
45
  | [GGUF](https://huggingface.co/mradermacher/GALAXY-16B-v1.0-GGUF/resolve/main/GALAXY-16B-v1.0.Q4_K_S.gguf) | Q4_K_S | 9.2 | fast, recommended |
46
  | [GGUF](https://huggingface.co/mradermacher/GALAXY-16B-v1.0-GGUF/resolve/main/GALAXY-16B-v1.0.Q4_K_M.gguf) | Q4_K_M | 9.7 | fast, recommended |
47
+ | [GGUF](https://huggingface.co/mradermacher/GALAXY-16B-v1.0-GGUF/resolve/main/GALAXY-16B-v1.0.Q5_K_S.gguf) | Q5_K_S | 11.1 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/GALAXY-16B-v1.0-GGUF/resolve/main/GALAXY-16B-v1.0.Q5_K_M.gguf) | Q5_K_M | 11.4 | |
49
  | [GGUF](https://huggingface.co/mradermacher/GALAXY-16B-v1.0-GGUF/resolve/main/GALAXY-16B-v1.0.Q6_K.gguf) | Q6_K | 13.2 | very good quality |
50
+ | [GGUF](https://huggingface.co/mradermacher/GALAXY-16B-v1.0-GGUF/resolve/main/GALAXY-16B-v1.0.Q8_0.gguf) | Q8_0 | 17.1 | fast, best quality |
51
 
52
  Here is a handy graph by ikawrakow comparing some lower-quality quant
53
  types (lower is better):