mradermacher commited on
Commit
6ca91e7
·
verified ·
1 Parent(s): 0e39b90

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -0
README.md CHANGED
@@ -40,8 +40,29 @@ more details, including on how to concatenate multi-part files.
40
  | Link | Type | Size/GB | Notes |
41
  |:-----|:-----|--------:|:------|
42
  | [GGUF](https://huggingface.co/mradermacher/ASearcher-Web-QwQ-i1-GGUF/resolve/main/ASearcher-Web-QwQ.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
 
 
 
 
 
 
 
43
  | [GGUF](https://huggingface.co/mradermacher/ASearcher-Web-QwQ-i1-GGUF/resolve/main/ASearcher-Web-QwQ.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better |
 
 
 
 
44
  | [GGUF](https://huggingface.co/mradermacher/ASearcher-Web-QwQ-i1-GGUF/resolve/main/ASearcher-Web-QwQ.i1-IQ3_M.gguf) | i1-IQ3_M | 14.9 | |
 
 
 
 
 
 
 
 
 
 
45
 
46
  Here is a handy graph by ikawrakow comparing some lower-quality quant
47
  types (lower is better):
 
40
  | Link | Type | Size/GB | Notes |
41
  |:-----|:-----|--------:|:------|
42
  | [GGUF](https://huggingface.co/mradermacher/ASearcher-Web-QwQ-i1-GGUF/resolve/main/ASearcher-Web-QwQ.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
43
+ | [GGUF](https://huggingface.co/mradermacher/ASearcher-Web-QwQ-i1-GGUF/resolve/main/ASearcher-Web-QwQ.i1-IQ1_S.gguf) | i1-IQ1_S | 7.4 | for the desperate |
44
+ | [GGUF](https://huggingface.co/mradermacher/ASearcher-Web-QwQ-i1-GGUF/resolve/main/ASearcher-Web-QwQ.i1-IQ1_M.gguf) | i1-IQ1_M | 8.0 | mostly desperate |
45
+ | [GGUF](https://huggingface.co/mradermacher/ASearcher-Web-QwQ-i1-GGUF/resolve/main/ASearcher-Web-QwQ.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/ASearcher-Web-QwQ-i1-GGUF/resolve/main/ASearcher-Web-QwQ.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.1 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/ASearcher-Web-QwQ-i1-GGUF/resolve/main/ASearcher-Web-QwQ.i1-IQ2_S.gguf) | i1-IQ2_S | 10.5 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/ASearcher-Web-QwQ-i1-GGUF/resolve/main/ASearcher-Web-QwQ.i1-IQ2_M.gguf) | i1-IQ2_M | 11.4 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/ASearcher-Web-QwQ-i1-GGUF/resolve/main/ASearcher-Web-QwQ.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.6 | very low quality |
50
  | [GGUF](https://huggingface.co/mradermacher/ASearcher-Web-QwQ-i1-GGUF/resolve/main/ASearcher-Web-QwQ.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better |
51
+ | [GGUF](https://huggingface.co/mradermacher/ASearcher-Web-QwQ-i1-GGUF/resolve/main/ASearcher-Web-QwQ.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality |
52
+ | [GGUF](https://huggingface.co/mradermacher/ASearcher-Web-QwQ-i1-GGUF/resolve/main/ASearcher-Web-QwQ.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.8 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/ASearcher-Web-QwQ-i1-GGUF/resolve/main/ASearcher-Web-QwQ.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.5 | IQ3_XS probably better |
54
+ | [GGUF](https://huggingface.co/mradermacher/ASearcher-Web-QwQ-i1-GGUF/resolve/main/ASearcher-Web-QwQ.i1-IQ3_S.gguf) | i1-IQ3_S | 14.5 | beats Q3_K* |
55
  | [GGUF](https://huggingface.co/mradermacher/ASearcher-Web-QwQ-i1-GGUF/resolve/main/ASearcher-Web-QwQ.i1-IQ3_M.gguf) | i1-IQ3_M | 14.9 | |
56
+ | [GGUF](https://huggingface.co/mradermacher/ASearcher-Web-QwQ-i1-GGUF/resolve/main/ASearcher-Web-QwQ.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.0 | IQ3_S probably better |
57
+ | [GGUF](https://huggingface.co/mradermacher/ASearcher-Web-QwQ-i1-GGUF/resolve/main/ASearcher-Web-QwQ.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.3 | IQ3_M probably better |
58
+ | [GGUF](https://huggingface.co/mradermacher/ASearcher-Web-QwQ-i1-GGUF/resolve/main/ASearcher-Web-QwQ.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.8 | |
59
+ | [GGUF](https://huggingface.co/mradermacher/ASearcher-Web-QwQ-i1-GGUF/resolve/main/ASearcher-Web-QwQ.i1-Q4_0.gguf) | i1-Q4_0 | 18.8 | fast, low quality |
60
+ | [GGUF](https://huggingface.co/mradermacher/ASearcher-Web-QwQ-i1-GGUF/resolve/main/ASearcher-Web-QwQ.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.9 | optimal size/speed/quality |
61
+ | [GGUF](https://huggingface.co/mradermacher/ASearcher-Web-QwQ-i1-GGUF/resolve/main/ASearcher-Web-QwQ.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.0 | fast, recommended |
62
+ | [GGUF](https://huggingface.co/mradermacher/ASearcher-Web-QwQ-i1-GGUF/resolve/main/ASearcher-Web-QwQ.i1-Q4_1.gguf) | i1-Q4_1 | 20.7 | |
63
+ | [GGUF](https://huggingface.co/mradermacher/ASearcher-Web-QwQ-i1-GGUF/resolve/main/ASearcher-Web-QwQ.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.7 | |
64
+ | [GGUF](https://huggingface.co/mradermacher/ASearcher-Web-QwQ-i1-GGUF/resolve/main/ASearcher-Web-QwQ.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.4 | |
65
+ | [GGUF](https://huggingface.co/mradermacher/ASearcher-Web-QwQ-i1-GGUF/resolve/main/ASearcher-Web-QwQ.i1-Q6_K.gguf) | i1-Q6_K | 27.0 | practically like static Q6_K |
66
 
67
  Here is a handy graph by ikawrakow comparing some lower-quality quant
68
  types (lower is better):