Hugging Face's logo

mradermacher
/
Huihui-MoE-46B-A14B-abliterated-GGUF

Transformers
GGUF
English
Mixture of Experts
Model card Files
xet
Community
mradermacher commited on
Commit
414f0bf
·
verified ·
1 Parent(s): d929a7a

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -45,10 +45,13 @@ more details, including on how to concatenate multi-part files.
45
  | [GGUF](https://huggingface.co/mradermacher/Huihui-MoE-46B-A14B-abliterated-GGUF/resolve/main/Huihui-MoE-46B-A14B-abliterated.Q3_K_S.gguf) | Q3_K_S | 20.5 | |
46
  | [GGUF](https://huggingface.co/mradermacher/Huihui-MoE-46B-A14B-abliterated-GGUF/resolve/main/Huihui-MoE-46B-A14B-abliterated.Q3_K_M.gguf) | Q3_K_M | 22.7 | lower quality |
47
  | [GGUF](https://huggingface.co/mradermacher/Huihui-MoE-46B-A14B-abliterated-GGUF/resolve/main/Huihui-MoE-46B-A14B-abliterated.Q3_K_L.gguf) | Q3_K_L | 24.5 | |
 
48
  | [GGUF](https://huggingface.co/mradermacher/Huihui-MoE-46B-A14B-abliterated-GGUF/resolve/main/Huihui-MoE-46B-A14B-abliterated.Q4_K_S.gguf) | Q4_K_S | 26.9 | fast, recommended |
49
  | [GGUF](https://huggingface.co/mradermacher/Huihui-MoE-46B-A14B-abliterated-GGUF/resolve/main/Huihui-MoE-46B-A14B-abliterated.Q4_K_M.gguf) | Q4_K_M | 28.5 | fast, recommended |
50
  | [GGUF](https://huggingface.co/mradermacher/Huihui-MoE-46B-A14B-abliterated-GGUF/resolve/main/Huihui-MoE-46B-A14B-abliterated.Q5_K_S.gguf) | Q5_K_S | 32.4 | |
 
51
  | [GGUF](https://huggingface.co/mradermacher/Huihui-MoE-46B-A14B-abliterated-GGUF/resolve/main/Huihui-MoE-46B-A14B-abliterated.Q6_K.gguf) | Q6_K | 38.5 | very good quality |
 
52
 
53
  Here is a handy graph by ikawrakow comparing some lower-quality quant
54
  types (lower is better):
 
45
  | [GGUF](https://huggingface.co/mradermacher/Huihui-MoE-46B-A14B-abliterated-GGUF/resolve/main/Huihui-MoE-46B-A14B-abliterated.Q3_K_S.gguf) | Q3_K_S | 20.5 | |
46
  | [GGUF](https://huggingface.co/mradermacher/Huihui-MoE-46B-A14B-abliterated-GGUF/resolve/main/Huihui-MoE-46B-A14B-abliterated.Q3_K_M.gguf) | Q3_K_M | 22.7 | lower quality |
47
  | [GGUF](https://huggingface.co/mradermacher/Huihui-MoE-46B-A14B-abliterated-GGUF/resolve/main/Huihui-MoE-46B-A14B-abliterated.Q3_K_L.gguf) | Q3_K_L | 24.5 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/Huihui-MoE-46B-A14B-abliterated-GGUF/resolve/main/Huihui-MoE-46B-A14B-abliterated.IQ4_XS.gguf) | IQ4_XS | 25.5 | |
49
  | [GGUF](https://huggingface.co/mradermacher/Huihui-MoE-46B-A14B-abliterated-GGUF/resolve/main/Huihui-MoE-46B-A14B-abliterated.Q4_K_S.gguf) | Q4_K_S | 26.9 | fast, recommended |
50
  | [GGUF](https://huggingface.co/mradermacher/Huihui-MoE-46B-A14B-abliterated-GGUF/resolve/main/Huihui-MoE-46B-A14B-abliterated.Q4_K_M.gguf) | Q4_K_M | 28.5 | fast, recommended |
51
  | [GGUF](https://huggingface.co/mradermacher/Huihui-MoE-46B-A14B-abliterated-GGUF/resolve/main/Huihui-MoE-46B-A14B-abliterated.Q5_K_S.gguf) | Q5_K_S | 32.4 | |
52
+ | [GGUF](https://huggingface.co/mradermacher/Huihui-MoE-46B-A14B-abliterated-GGUF/resolve/main/Huihui-MoE-46B-A14B-abliterated.Q5_K_M.gguf) | Q5_K_M | 33.4 | |
53
  | [GGUF](https://huggingface.co/mradermacher/Huihui-MoE-46B-A14B-abliterated-GGUF/resolve/main/Huihui-MoE-46B-A14B-abliterated.Q6_K.gguf) | Q6_K | 38.5 | very good quality |
54
+ | [GGUF](https://huggingface.co/mradermacher/Huihui-MoE-46B-A14B-abliterated-GGUF/resolve/main/Huihui-MoE-46B-A14B-abliterated.Q8_0.gguf) | Q8_0 | 49.9 | fast, best quality |
55
 
56
  Here is a handy graph by ikawrakow comparing some lower-quality quant
57
  types (lower is better):