Hugging Face's logo

mradermacher
/
WestLakeMultiverse-12B-MoE-GGUF

Transformers
GGUF
English
Mixture of Experts
frankenmoe
Merge
mergekit
lazymergekit
allknowingroger/MultiverseEx26-7B-slerp
senseable/WestLake-7B-v2
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
a542909
·
verified ·
1 Parent(s): 7c86402

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -0
README.md CHANGED
@@ -40,7 +40,14 @@ more details, including on how to concatenate multi-part files.
40
  | [GGUF](https://huggingface.co/mradermacher/WestLakeMultiverse-12B-MoE-GGUF/resolve/main/WestLakeMultiverse-12B-MoE.Q2_K.gguf) | Q2_K | 4.9 | |
41
  | [GGUF](https://huggingface.co/mradermacher/WestLakeMultiverse-12B-MoE-GGUF/resolve/main/WestLakeMultiverse-12B-MoE.Q3_K_S.gguf) | Q3_K_S | 5.7 | |
42
  | [GGUF](https://huggingface.co/mradermacher/WestLakeMultiverse-12B-MoE-GGUF/resolve/main/WestLakeMultiverse-12B-MoE.Q3_K_M.gguf) | Q3_K_M | 6.3 | lower quality |
 
 
43
  | [GGUF](https://huggingface.co/mradermacher/WestLakeMultiverse-12B-MoE-GGUF/resolve/main/WestLakeMultiverse-12B-MoE.Q4_K_S.gguf) | Q4_K_S | 7.4 | fast, recommended |
 
 
 
 
 
44
 
45
  Here is a handy graph by ikawrakow comparing some lower-quality quant
46
  types (lower is better):
 
40
  | [GGUF](https://huggingface.co/mradermacher/WestLakeMultiverse-12B-MoE-GGUF/resolve/main/WestLakeMultiverse-12B-MoE.Q2_K.gguf) | Q2_K | 4.9 | |
41
  | [GGUF](https://huggingface.co/mradermacher/WestLakeMultiverse-12B-MoE-GGUF/resolve/main/WestLakeMultiverse-12B-MoE.Q3_K_S.gguf) | Q3_K_S | 5.7 | |
42
  | [GGUF](https://huggingface.co/mradermacher/WestLakeMultiverse-12B-MoE-GGUF/resolve/main/WestLakeMultiverse-12B-MoE.Q3_K_M.gguf) | Q3_K_M | 6.3 | lower quality |
43
+ | [GGUF](https://huggingface.co/mradermacher/WestLakeMultiverse-12B-MoE-GGUF/resolve/main/WestLakeMultiverse-12B-MoE.Q3_K_L.gguf) | Q3_K_L | 6.8 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/WestLakeMultiverse-12B-MoE-GGUF/resolve/main/WestLakeMultiverse-12B-MoE.IQ4_XS.gguf) | IQ4_XS | 7.1 | |
45
  | [GGUF](https://huggingface.co/mradermacher/WestLakeMultiverse-12B-MoE-GGUF/resolve/main/WestLakeMultiverse-12B-MoE.Q4_K_S.gguf) | Q4_K_S | 7.4 | fast, recommended |
46
+ | [GGUF](https://huggingface.co/mradermacher/WestLakeMultiverse-12B-MoE-GGUF/resolve/main/WestLakeMultiverse-12B-MoE.Q4_K_M.gguf) | Q4_K_M | 7.9 | fast, recommended |
47
+ | [GGUF](https://huggingface.co/mradermacher/WestLakeMultiverse-12B-MoE-GGUF/resolve/main/WestLakeMultiverse-12B-MoE.Q5_K_S.gguf) | Q5_K_S | 9.0 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/WestLakeMultiverse-12B-MoE-GGUF/resolve/main/WestLakeMultiverse-12B-MoE.Q5_K_M.gguf) | Q5_K_M | 9.2 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/WestLakeMultiverse-12B-MoE-GGUF/resolve/main/WestLakeMultiverse-12B-MoE.Q6_K.gguf) | Q6_K | 10.7 | very good quality |
50
+ | [GGUF](https://huggingface.co/mradermacher/WestLakeMultiverse-12B-MoE-GGUF/resolve/main/WestLakeMultiverse-12B-MoE.Q8_0.gguf) | Q8_0 | 13.8 | fast, best quality |
51
 
52
  Here is a handy graph by ikawrakow comparing some lower-quality quant
53
  types (lower is better):