mradermacher commited on
Commit
455d88e
·
verified ·
1 Parent(s): 62d8bac

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -45,8 +45,11 @@ more details, including on how to concatenate multi-part files.
45
  | [GGUF](https://huggingface.co/mradermacher/Assistant_Pepe_70B-i1-GGUF/resolve/main/Assistant_Pepe_70B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 19.2 | |
46
  | [GGUF](https://huggingface.co/mradermacher/Assistant_Pepe_70B-i1-GGUF/resolve/main/Assistant_Pepe_70B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 21.2 | |
47
  | [GGUF](https://huggingface.co/mradermacher/Assistant_Pepe_70B-i1-GGUF/resolve/main/Assistant_Pepe_70B.i1-IQ2_M.gguf) | i1-IQ2_M | 24.2 | |
 
48
  | [GGUF](https://huggingface.co/mradermacher/Assistant_Pepe_70B-i1-GGUF/resolve/main/Assistant_Pepe_70B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 29.4 | |
 
49
  | [GGUF](https://huggingface.co/mradermacher/Assistant_Pepe_70B-i1-GGUF/resolve/main/Assistant_Pepe_70B.i1-IQ3_M.gguf) | i1-IQ3_M | 32.0 | |
 
50
 
51
  Here is a handy graph by ikawrakow comparing some lower-quality quant
52
  types (lower is better):
 
45
  | [GGUF](https://huggingface.co/mradermacher/Assistant_Pepe_70B-i1-GGUF/resolve/main/Assistant_Pepe_70B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 19.2 | |
46
  | [GGUF](https://huggingface.co/mradermacher/Assistant_Pepe_70B-i1-GGUF/resolve/main/Assistant_Pepe_70B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 21.2 | |
47
  | [GGUF](https://huggingface.co/mradermacher/Assistant_Pepe_70B-i1-GGUF/resolve/main/Assistant_Pepe_70B.i1-IQ2_M.gguf) | i1-IQ2_M | 24.2 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/Assistant_Pepe_70B-i1-GGUF/resolve/main/Assistant_Pepe_70B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 24.6 | very low quality |
49
  | [GGUF](https://huggingface.co/mradermacher/Assistant_Pepe_70B-i1-GGUF/resolve/main/Assistant_Pepe_70B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 29.4 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/Assistant_Pepe_70B-i1-GGUF/resolve/main/Assistant_Pepe_70B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 31.0 | IQ3_XS probably better |
51
  | [GGUF](https://huggingface.co/mradermacher/Assistant_Pepe_70B-i1-GGUF/resolve/main/Assistant_Pepe_70B.i1-IQ3_M.gguf) | i1-IQ3_M | 32.0 | |
52
+ | [GGUF](https://huggingface.co/mradermacher/Assistant_Pepe_70B-i1-GGUF/resolve/main/Assistant_Pepe_70B.i1-Q4_1.gguf) | i1-Q4_1 | 44.4 | |
53
 
54
  Here is a handy graph by ikawrakow comparing some lower-quality quant
55
  types (lower is better):