Hugging Face's logo

mradermacher
/
Capybara-Tess-Yi-34B-200K-DARE-Ties-GGUF

Transformers
GGUF
English
Merge
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
8387a70
·
verified ·
1 Parent(s): d72c971

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -37,11 +37,13 @@ more details, including on how to concatenate multi-part files.
37
  | [GGUF](https://huggingface.co/mradermacher/Capybara-Tess-Yi-34B-200K-DARE-Ties-GGUF/resolve/main/Capybara-Tess-Yi-34B-200K-DARE-Ties.Q3_K_S.gguf) | Q3_K_S | 15.1 | |
38
  | [GGUF](https://huggingface.co/mradermacher/Capybara-Tess-Yi-34B-200K-DARE-Ties-GGUF/resolve/main/Capybara-Tess-Yi-34B-200K-DARE-Ties.Q3_K_M.gguf) | Q3_K_M | 16.8 | lower quality |
39
  | [GGUF](https://huggingface.co/mradermacher/Capybara-Tess-Yi-34B-200K-DARE-Ties-GGUF/resolve/main/Capybara-Tess-Yi-34B-200K-DARE-Ties.Q3_K_L.gguf) | Q3_K_L | 18.2 | |
 
40
  | [GGUF](https://huggingface.co/mradermacher/Capybara-Tess-Yi-34B-200K-DARE-Ties-GGUF/resolve/main/Capybara-Tess-Yi-34B-200K-DARE-Ties.Q4_K_S.gguf) | Q4_K_S | 19.7 | fast, recommended |
41
  | [GGUF](https://huggingface.co/mradermacher/Capybara-Tess-Yi-34B-200K-DARE-Ties-GGUF/resolve/main/Capybara-Tess-Yi-34B-200K-DARE-Ties.Q4_K_M.gguf) | Q4_K_M | 20.8 | fast, recommended |
42
  | [GGUF](https://huggingface.co/mradermacher/Capybara-Tess-Yi-34B-200K-DARE-Ties-GGUF/resolve/main/Capybara-Tess-Yi-34B-200K-DARE-Ties.Q5_K_S.gguf) | Q5_K_S | 23.8 | |
43
  | [GGUF](https://huggingface.co/mradermacher/Capybara-Tess-Yi-34B-200K-DARE-Ties-GGUF/resolve/main/Capybara-Tess-Yi-34B-200K-DARE-Ties.Q5_K_M.gguf) | Q5_K_M | 24.4 | |
44
  | [GGUF](https://huggingface.co/mradermacher/Capybara-Tess-Yi-34B-200K-DARE-Ties-GGUF/resolve/main/Capybara-Tess-Yi-34B-200K-DARE-Ties.Q6_K.gguf) | Q6_K | 28.3 | very good quality |
 
45
 
46
  Here is a handy graph by ikawrakow comparing some lower-quality quant
47
  types (lower is better):
 
37
  | [GGUF](https://huggingface.co/mradermacher/Capybara-Tess-Yi-34B-200K-DARE-Ties-GGUF/resolve/main/Capybara-Tess-Yi-34B-200K-DARE-Ties.Q3_K_S.gguf) | Q3_K_S | 15.1 | |
38
  | [GGUF](https://huggingface.co/mradermacher/Capybara-Tess-Yi-34B-200K-DARE-Ties-GGUF/resolve/main/Capybara-Tess-Yi-34B-200K-DARE-Ties.Q3_K_M.gguf) | Q3_K_M | 16.8 | lower quality |
39
  | [GGUF](https://huggingface.co/mradermacher/Capybara-Tess-Yi-34B-200K-DARE-Ties-GGUF/resolve/main/Capybara-Tess-Yi-34B-200K-DARE-Ties.Q3_K_L.gguf) | Q3_K_L | 18.2 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/Capybara-Tess-Yi-34B-200K-DARE-Ties-GGUF/resolve/main/Capybara-Tess-Yi-34B-200K-DARE-Ties.IQ4_XS.gguf) | IQ4_XS | 18.7 | |
41
  | [GGUF](https://huggingface.co/mradermacher/Capybara-Tess-Yi-34B-200K-DARE-Ties-GGUF/resolve/main/Capybara-Tess-Yi-34B-200K-DARE-Ties.Q4_K_S.gguf) | Q4_K_S | 19.7 | fast, recommended |
42
  | [GGUF](https://huggingface.co/mradermacher/Capybara-Tess-Yi-34B-200K-DARE-Ties-GGUF/resolve/main/Capybara-Tess-Yi-34B-200K-DARE-Ties.Q4_K_M.gguf) | Q4_K_M | 20.8 | fast, recommended |
43
  | [GGUF](https://huggingface.co/mradermacher/Capybara-Tess-Yi-34B-200K-DARE-Ties-GGUF/resolve/main/Capybara-Tess-Yi-34B-200K-DARE-Ties.Q5_K_S.gguf) | Q5_K_S | 23.8 | |
44
  | [GGUF](https://huggingface.co/mradermacher/Capybara-Tess-Yi-34B-200K-DARE-Ties-GGUF/resolve/main/Capybara-Tess-Yi-34B-200K-DARE-Ties.Q5_K_M.gguf) | Q5_K_M | 24.4 | |
45
  | [GGUF](https://huggingface.co/mradermacher/Capybara-Tess-Yi-34B-200K-DARE-Ties-GGUF/resolve/main/Capybara-Tess-Yi-34B-200K-DARE-Ties.Q6_K.gguf) | Q6_K | 28.3 | very good quality |
46
+ | [GGUF](https://huggingface.co/mradermacher/Capybara-Tess-Yi-34B-200K-DARE-Ties-GGUF/resolve/main/Capybara-Tess-Yi-34B-200K-DARE-Ties.Q8_0.gguf) | Q8_0 | 36.6 | fast, best quality |
47
 
48
  Here is a handy graph by ikawrakow comparing some lower-quality quant
49
  types (lower is better):