Hugging Face's logo

mradermacher
/
Vengeance-22B-i1-GGUF

Transformers
GGUF
English
mergekit
Merge
imatrix
conversational
Model card Files
xet
Community
mradermacher commited on
Commit
a567d4b
·
verified ·
1 Parent(s): dae7492

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -0
README.md CHANGED
@@ -34,13 +34,20 @@ more details, including on how to concatenate multi-part files.
34
 
35
  | Link | Type | Size/GB | Notes |
36
  |:-----|:-----|--------:|:------|
 
 
 
37
  | [GGUF](https://huggingface.co/mradermacher/Vengeance-22B-i1-GGUF/resolve/main/Vengeance-22B.i1-IQ2_M.gguf) | i1-IQ2_M | 7.7 | |
38
  | [GGUF](https://huggingface.co/mradermacher/Vengeance-22B-i1-GGUF/resolve/main/Vengeance-22B.i1-Q2_K.gguf) | i1-Q2_K | 8.4 | IQ3_XXS probably better |
39
  | [GGUF](https://huggingface.co/mradermacher/Vengeance-22B-i1-GGUF/resolve/main/Vengeance-22B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 8.7 | lower quality |
 
40
  | [GGUF](https://huggingface.co/mradermacher/Vengeance-22B-i1-GGUF/resolve/main/Vengeance-22B.i1-IQ3_M.gguf) | i1-IQ3_M | 10.2 | |
41
  | [GGUF](https://huggingface.co/mradermacher/Vengeance-22B-i1-GGUF/resolve/main/Vengeance-22B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 10.9 | IQ3_S probably better |
 
 
42
  | [GGUF](https://huggingface.co/mradermacher/Vengeance-22B-i1-GGUF/resolve/main/Vengeance-22B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 12.8 | optimal size/speed/quality |
43
  | [GGUF](https://huggingface.co/mradermacher/Vengeance-22B-i1-GGUF/resolve/main/Vengeance-22B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 13.4 | fast, recommended |
 
44
  | [GGUF](https://huggingface.co/mradermacher/Vengeance-22B-i1-GGUF/resolve/main/Vengeance-22B.i1-Q6_K.gguf) | i1-Q6_K | 18.4 | practically like static Q6_K |
45
 
46
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
34
 
35
  | Link | Type | Size/GB | Notes |
36
  |:-----|:-----|--------:|:------|
37
+ | [GGUF](https://huggingface.co/mradermacher/Vengeance-22B-i1-GGUF/resolve/main/Vengeance-22B.i1-IQ1_M.gguf) | i1-IQ1_M | 5.4 | mostly desperate |
38
+ | [GGUF](https://huggingface.co/mradermacher/Vengeance-22B-i1-GGUF/resolve/main/Vengeance-22B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 6.1 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/Vengeance-22B-i1-GGUF/resolve/main/Vengeance-22B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 6.7 | |
40
  | [GGUF](https://huggingface.co/mradermacher/Vengeance-22B-i1-GGUF/resolve/main/Vengeance-22B.i1-IQ2_M.gguf) | i1-IQ2_M | 7.7 | |
41
  | [GGUF](https://huggingface.co/mradermacher/Vengeance-22B-i1-GGUF/resolve/main/Vengeance-22B.i1-Q2_K.gguf) | i1-Q2_K | 8.4 | IQ3_XXS probably better |
42
  | [GGUF](https://huggingface.co/mradermacher/Vengeance-22B-i1-GGUF/resolve/main/Vengeance-22B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 8.7 | lower quality |
43
+ | [GGUF](https://huggingface.co/mradermacher/Vengeance-22B-i1-GGUF/resolve/main/Vengeance-22B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 9.7 | IQ3_XS probably better |
44
  | [GGUF](https://huggingface.co/mradermacher/Vengeance-22B-i1-GGUF/resolve/main/Vengeance-22B.i1-IQ3_M.gguf) | i1-IQ3_M | 10.2 | |
45
  | [GGUF](https://huggingface.co/mradermacher/Vengeance-22B-i1-GGUF/resolve/main/Vengeance-22B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 10.9 | IQ3_S probably better |
46
+ | [GGUF](https://huggingface.co/mradermacher/Vengeance-22B-i1-GGUF/resolve/main/Vengeance-22B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 11.8 | IQ3_M probably better |
47
+ | [GGUF](https://huggingface.co/mradermacher/Vengeance-22B-i1-GGUF/resolve/main/Vengeance-22B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 12.0 | |
48
  | [GGUF](https://huggingface.co/mradermacher/Vengeance-22B-i1-GGUF/resolve/main/Vengeance-22B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 12.8 | optimal size/speed/quality |
49
  | [GGUF](https://huggingface.co/mradermacher/Vengeance-22B-i1-GGUF/resolve/main/Vengeance-22B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 13.4 | fast, recommended |
50
+ | [GGUF](https://huggingface.co/mradermacher/Vengeance-22B-i1-GGUF/resolve/main/Vengeance-22B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 15.4 | |
51
  | [GGUF](https://huggingface.co/mradermacher/Vengeance-22B-i1-GGUF/resolve/main/Vengeance-22B.i1-Q6_K.gguf) | i1-Q6_K | 18.4 | practically like static Q6_K |
52
 
53
  Here is a handy graph by ikawrakow comparing some lower-quality quant