mradermacher commited on
Commit
34763fe
1 Parent(s): 4dad4f1

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -0
README.md CHANGED
@@ -37,12 +37,24 @@ more details, including on how to concatenate multi-part files.
37
 
38
  | Link | Type | Size/GB | Notes |
39
  |:-----|:-----|--------:|:------|
 
 
 
40
  | [GGUF](https://huggingface.co/mradermacher/WukongV2-Mixtral-8x7B-V0.1-i1-GGUF/resolve/main/WukongV2-Mixtral-8x7B-V0.1.i1-IQ2_M.gguf) | i1-IQ2_M | 15.6 | |
41
  | [GGUF](https://huggingface.co/mradermacher/WukongV2-Mixtral-8x7B-V0.1-i1-GGUF/resolve/main/WukongV2-Mixtral-8x7B-V0.1.i1-Q2_K.gguf) | i1-Q2_K | 17.4 | IQ3_XXS probably better |
42
  | [GGUF](https://huggingface.co/mradermacher/WukongV2-Mixtral-8x7B-V0.1-i1-GGUF/resolve/main/WukongV2-Mixtral-8x7B-V0.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 18.3 | lower quality |
 
 
 
 
43
  | [GGUF](https://huggingface.co/mradermacher/WukongV2-Mixtral-8x7B-V0.1-i1-GGUF/resolve/main/WukongV2-Mixtral-8x7B-V0.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 22.6 | IQ3_S probably better |
 
 
 
44
  | [GGUF](https://huggingface.co/mradermacher/WukongV2-Mixtral-8x7B-V0.1-i1-GGUF/resolve/main/WukongV2-Mixtral-8x7B-V0.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 26.8 | optimal size/speed/quality |
45
  | [GGUF](https://huggingface.co/mradermacher/WukongV2-Mixtral-8x7B-V0.1-i1-GGUF/resolve/main/WukongV2-Mixtral-8x7B-V0.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 28.5 | fast, recommended |
 
 
46
  | [GGUF](https://huggingface.co/mradermacher/WukongV2-Mixtral-8x7B-V0.1-i1-GGUF/resolve/main/WukongV2-Mixtral-8x7B-V0.1.i1-Q6_K.gguf) | i1-Q6_K | 38.5 | practically like static Q6_K |
47
 
48
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
37
 
38
  | Link | Type | Size/GB | Notes |
39
  |:-----|:-----|--------:|:------|
40
+ | [GGUF](https://huggingface.co/mradermacher/WukongV2-Mixtral-8x7B-V0.1-i1-GGUF/resolve/main/WukongV2-Mixtral-8x7B-V0.1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 12.7 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/WukongV2-Mixtral-8x7B-V0.1-i1-GGUF/resolve/main/WukongV2-Mixtral-8x7B-V0.1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 14.0 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/WukongV2-Mixtral-8x7B-V0.1-i1-GGUF/resolve/main/WukongV2-Mixtral-8x7B-V0.1.i1-IQ2_S.gguf) | i1-IQ2_S | 14.2 | |
43
  | [GGUF](https://huggingface.co/mradermacher/WukongV2-Mixtral-8x7B-V0.1-i1-GGUF/resolve/main/WukongV2-Mixtral-8x7B-V0.1.i1-IQ2_M.gguf) | i1-IQ2_M | 15.6 | |
44
  | [GGUF](https://huggingface.co/mradermacher/WukongV2-Mixtral-8x7B-V0.1-i1-GGUF/resolve/main/WukongV2-Mixtral-8x7B-V0.1.i1-Q2_K.gguf) | i1-Q2_K | 17.4 | IQ3_XXS probably better |
45
  | [GGUF](https://huggingface.co/mradermacher/WukongV2-Mixtral-8x7B-V0.1-i1-GGUF/resolve/main/WukongV2-Mixtral-8x7B-V0.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 18.3 | lower quality |
46
+ | [GGUF](https://huggingface.co/mradermacher/WukongV2-Mixtral-8x7B-V0.1-i1-GGUF/resolve/main/WukongV2-Mixtral-8x7B-V0.1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 19.5 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/WukongV2-Mixtral-8x7B-V0.1-i1-GGUF/resolve/main/WukongV2-Mixtral-8x7B-V0.1.i1-IQ3_S.gguf) | i1-IQ3_S | 20.5 | beats Q3_K* |
48
+ | [GGUF](https://huggingface.co/mradermacher/WukongV2-Mixtral-8x7B-V0.1-i1-GGUF/resolve/main/WukongV2-Mixtral-8x7B-V0.1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 20.5 | IQ3_XS probably better |
49
+ | [GGUF](https://huggingface.co/mradermacher/WukongV2-Mixtral-8x7B-V0.1-i1-GGUF/resolve/main/WukongV2-Mixtral-8x7B-V0.1.i1-IQ3_M.gguf) | i1-IQ3_M | 21.5 | |
50
  | [GGUF](https://huggingface.co/mradermacher/WukongV2-Mixtral-8x7B-V0.1-i1-GGUF/resolve/main/WukongV2-Mixtral-8x7B-V0.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 22.6 | IQ3_S probably better |
51
+ | [GGUF](https://huggingface.co/mradermacher/WukongV2-Mixtral-8x7B-V0.1-i1-GGUF/resolve/main/WukongV2-Mixtral-8x7B-V0.1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 24.3 | IQ3_M probably better |
52
+ | [GGUF](https://huggingface.co/mradermacher/WukongV2-Mixtral-8x7B-V0.1-i1-GGUF/resolve/main/WukongV2-Mixtral-8x7B-V0.1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 25.2 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/WukongV2-Mixtral-8x7B-V0.1-i1-GGUF/resolve/main/WukongV2-Mixtral-8x7B-V0.1.i1-Q4_0.gguf) | i1-Q4_0 | 26.7 | fast, low quality |
54
  | [GGUF](https://huggingface.co/mradermacher/WukongV2-Mixtral-8x7B-V0.1-i1-GGUF/resolve/main/WukongV2-Mixtral-8x7B-V0.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 26.8 | optimal size/speed/quality |
55
  | [GGUF](https://huggingface.co/mradermacher/WukongV2-Mixtral-8x7B-V0.1-i1-GGUF/resolve/main/WukongV2-Mixtral-8x7B-V0.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 28.5 | fast, recommended |
56
+ | [GGUF](https://huggingface.co/mradermacher/WukongV2-Mixtral-8x7B-V0.1-i1-GGUF/resolve/main/WukongV2-Mixtral-8x7B-V0.1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 32.3 | |
57
+ | [GGUF](https://huggingface.co/mradermacher/WukongV2-Mixtral-8x7B-V0.1-i1-GGUF/resolve/main/WukongV2-Mixtral-8x7B-V0.1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 33.3 | |
58
  | [GGUF](https://huggingface.co/mradermacher/WukongV2-Mixtral-8x7B-V0.1-i1-GGUF/resolve/main/WukongV2-Mixtral-8x7B-V0.1.i1-Q6_K.gguf) | i1-Q6_K | 38.5 | practically like static Q6_K |
59
 
60
  Here is a handy graph by ikawrakow comparing some lower-quality quant