Hugging Face's logo

mradermacher
/
TaoPassthrough-15B-s-GGUF

Transformers
GGUF
English
Merge
mergekit
lazymergekit
zhengr/MixTAO-7Bx2-MoE-v8.1
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
56e3be6
•
1 Parent(s): 2eafe7f

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -39,14 +39,13 @@ more details, including on how to concatenate multi-part files.
39
  | [GGUF](https://huggingface.co/mradermacher/TaoPassthrough-15B-s-GGUF/resolve/main/TaoPassthrough-15B-s.IQ4_XS.gguf) | IQ4_XS | 10.6 | |
40
  | [GGUF](https://huggingface.co/mradermacher/TaoPassthrough-15B-s-GGUF/resolve/main/TaoPassthrough-15B-s.Q4_0.gguf) | Q4_0 | 11.1 | fast, low quality |
41
  | [GGUF](https://huggingface.co/mradermacher/TaoPassthrough-15B-s-GGUF/resolve/main/TaoPassthrough-15B-s.Q4_K_S.gguf) | Q4_K_S | 11.2 | fast, recommended |
42
- | [GGUF](https://huggingface.co/mradermacher/TaoPassthrough-15B-s-GGUF/resolve/main/TaoPassthrough-15B-s.IQ4_NL.gguf) | IQ4_NL | 11.2 | slightly worse than Q4_K_S |
43
  | [GGUF](https://huggingface.co/mradermacher/TaoPassthrough-15B-s-GGUF/resolve/main/TaoPassthrough-15B-s.Q4_K_M.gguf) | Q4_K_M | 11.8 | fast, recommended |
44
  | [GGUF](https://huggingface.co/mradermacher/TaoPassthrough-15B-s-GGUF/resolve/main/TaoPassthrough-15B-s.Q5_K_S.gguf) | Q5_K_S | 13.5 | |
45
  | [GGUF](https://huggingface.co/mradermacher/TaoPassthrough-15B-s-GGUF/resolve/main/TaoPassthrough-15B-s.Q5_K_M.gguf) | Q5_K_M | 13.9 | |
46
  | [GGUF](https://huggingface.co/mradermacher/TaoPassthrough-15B-s-GGUF/resolve/main/TaoPassthrough-15B-s.Q6_K.gguf) | Q6_K | 16.0 | very good quality |
47
  | [GGUF](https://huggingface.co/mradermacher/TaoPassthrough-15B-s-GGUF/resolve/main/TaoPassthrough-15B-s.Q8_0.gguf) | Q8_0 | 20.6 | fast, best quality |
48
 
49
-
50
  Here is a handy graph by ikawrakow comparing some lower-quality quant
51
  types (lower is better):
52
 
 
39
  | [GGUF](https://huggingface.co/mradermacher/TaoPassthrough-15B-s-GGUF/resolve/main/TaoPassthrough-15B-s.IQ4_XS.gguf) | IQ4_XS | 10.6 | |
40
  | [GGUF](https://huggingface.co/mradermacher/TaoPassthrough-15B-s-GGUF/resolve/main/TaoPassthrough-15B-s.Q4_0.gguf) | Q4_0 | 11.1 | fast, low quality |
41
  | [GGUF](https://huggingface.co/mradermacher/TaoPassthrough-15B-s-GGUF/resolve/main/TaoPassthrough-15B-s.Q4_K_S.gguf) | Q4_K_S | 11.2 | fast, recommended |
42
+ | [GGUF](https://huggingface.co/mradermacher/TaoPassthrough-15B-s-GGUF/resolve/main/TaoPassthrough-15B-s.IQ4_NL.gguf) | IQ4_NL | 11.2 | prefer IQ4_XS |
43
  | [GGUF](https://huggingface.co/mradermacher/TaoPassthrough-15B-s-GGUF/resolve/main/TaoPassthrough-15B-s.Q4_K_M.gguf) | Q4_K_M | 11.8 | fast, recommended |
44
  | [GGUF](https://huggingface.co/mradermacher/TaoPassthrough-15B-s-GGUF/resolve/main/TaoPassthrough-15B-s.Q5_K_S.gguf) | Q5_K_S | 13.5 | |
45
  | [GGUF](https://huggingface.co/mradermacher/TaoPassthrough-15B-s-GGUF/resolve/main/TaoPassthrough-15B-s.Q5_K_M.gguf) | Q5_K_M | 13.9 | |
46
  | [GGUF](https://huggingface.co/mradermacher/TaoPassthrough-15B-s-GGUF/resolve/main/TaoPassthrough-15B-s.Q6_K.gguf) | Q6_K | 16.0 | very good quality |
47
  | [GGUF](https://huggingface.co/mradermacher/TaoPassthrough-15B-s-GGUF/resolve/main/TaoPassthrough-15B-s.Q8_0.gguf) | Q8_0 | 20.6 | fast, best quality |
48
 
 
49
  Here is a handy graph by ikawrakow comparing some lower-quality quant
50
  types (lower is better):
51