mradermacher commited on
Commit
1056311
·
verified ·
1 Parent(s): 777a414

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -0
README.md CHANGED
@@ -46,21 +46,28 @@ more details, including on how to concatenate multi-part files.
46
  | Link | Type | Size/GB | Notes |
47
  |:-----|:-----|--------:|:------|
48
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
 
49
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-IQ1_M.gguf) | i1-IQ1_M | 7.7 | mostly desperate |
50
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 8.8 | |
51
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 9.7 | |
 
52
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-IQ2_M.gguf) | i1-IQ2_M | 11.0 | |
53
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.2 | very low quality |
54
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-Q2_K.gguf) | i1-Q2_K | 12.0 | IQ3_XXS probably better |
55
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.6 | lower quality |
 
56
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.1 | IQ3_XS probably better |
 
57
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-IQ3_M.gguf) | i1-IQ3_M | 14.5 | |
58
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 15.6 | IQ3_S probably better |
59
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 16.9 | IQ3_M probably better |
60
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.3 | |
 
61
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.4 | optimal size/speed/quality |
62
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 19.4 | fast, recommended |
 
63
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.2 | |
 
64
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-Q6_K.gguf) | i1-Q6_K | 26.4 | practically like static Q6_K |
65
 
66
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
46
  | Link | Type | Size/GB | Notes |
47
  |:-----|:-----|--------:|:------|
48
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
49
+ | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-IQ1_S.gguf) | i1-IQ1_S | 7.1 | for the desperate |
50
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-IQ1_M.gguf) | i1-IQ1_M | 7.7 | mostly desperate |
51
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 8.8 | |
52
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 9.7 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-IQ2_S.gguf) | i1-IQ2_S | 10.1 | |
54
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-IQ2_M.gguf) | i1-IQ2_M | 11.0 | |
55
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.2 | very low quality |
56
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-Q2_K.gguf) | i1-Q2_K | 12.0 | IQ3_XXS probably better |
57
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.6 | lower quality |
58
+ | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.4 | |
59
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.1 | IQ3_XS probably better |
60
+ | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-IQ3_S.gguf) | i1-IQ3_S | 14.1 | beats Q3_K* |
61
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-IQ3_M.gguf) | i1-IQ3_M | 14.5 | |
62
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 15.6 | IQ3_S probably better |
63
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 16.9 | IQ3_M probably better |
64
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.3 | |
65
+ | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-Q4_0.gguf) | i1-Q4_0 | 18.3 | fast, low quality |
66
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.4 | optimal size/speed/quality |
67
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 19.4 | fast, recommended |
68
+ | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-Q4_1.gguf) | i1-Q4_1 | 20.2 | |
69
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.2 | |
70
+ | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 22.8 | |
71
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-4.0.1-32B-i1-GGUF/resolve/main/EXAONE-4.0.1-32B.i1-Q6_K.gguf) | i1-Q6_K | 26.4 | practically like static Q6_K |
72
 
73
  Here is a handy graph by ikawrakow comparing some lower-quality quant