Hugging Face's logo

mradermacher
/
Impish-LongPen-12B-i1-GGUF

Transformers
GGUF
English
mergekit
Merge
imatrix
Model card Files
xet
Community
mradermacher commited on
Commit
f0e8249
·
verified ·
1 Parent(s): 5cfc29a

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -0
README.md CHANGED
@@ -41,19 +41,29 @@ more details, including on how to concatenate multi-part files.
41
  | Link | Type | Size/GB | Notes |
42
  |:-----|:-----|--------:|:------|
43
  | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
 
44
  | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-IQ1_M.gguf) | i1-IQ1_M | 3.3 | mostly desperate |
45
  | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.7 | |
 
 
46
  | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-IQ2_M.gguf) | i1-IQ2_M | 4.5 | |
47
  | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 4.6 | very low quality |
48
  | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-Q2_K.gguf) | i1-Q2_K | 4.9 | IQ3_XXS probably better |
49
  | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.0 | lower quality |
 
50
  | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.6 | IQ3_XS probably better |
 
51
  | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-IQ3_M.gguf) | i1-IQ3_M | 5.8 | |
52
  | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.2 | IQ3_S probably better |
 
53
  | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 6.8 | |
 
54
  | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 7.2 | prefer IQ4_XS |
55
  | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.2 | optimal size/speed/quality |
56
  | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 7.6 | fast, recommended |
 
 
 
57
  | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-Q6_K.gguf) | i1-Q6_K | 10.2 | practically like static Q6_K |
58
 
59
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
41
  | Link | Type | Size/GB | Notes |
42
  |:-----|:-----|--------:|:------|
43
  | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
44
+ | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-IQ1_S.gguf) | i1-IQ1_S | 3.1 | for the desperate |
45
  | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-IQ1_M.gguf) | i1-IQ1_M | 3.3 | mostly desperate |
46
  | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.7 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.0 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-IQ2_S.gguf) | i1-IQ2_S | 4.2 | |
49
  | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-IQ2_M.gguf) | i1-IQ2_M | 4.5 | |
50
  | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 4.6 | very low quality |
51
  | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-Q2_K.gguf) | i1-Q2_K | 4.9 | IQ3_XXS probably better |
52
  | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.0 | lower quality |
53
+ | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.4 | |
54
  | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.6 | IQ3_XS probably better |
55
+ | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-IQ3_S.gguf) | i1-IQ3_S | 5.7 | beats Q3_K* |
56
  | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-IQ3_M.gguf) | i1-IQ3_M | 5.8 | |
57
  | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.2 | IQ3_S probably better |
58
+ | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 6.7 | IQ3_M probably better |
59
  | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 6.8 | |
60
+ | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-Q4_0.gguf) | i1-Q4_0 | 7.2 | fast, low quality |
61
  | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 7.2 | prefer IQ4_XS |
62
  | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.2 | optimal size/speed/quality |
63
  | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 7.6 | fast, recommended |
64
+ | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-Q4_1.gguf) | i1-Q4_1 | 7.9 | |
65
+ | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 8.6 | |
66
+ | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 8.8 | |
67
  | [GGUF](https://huggingface.co/mradermacher/Impish-LongPen-12B-i1-GGUF/resolve/main/Impish-LongPen-12B.i1-Q6_K.gguf) | i1-Q6_K | 10.2 | practically like static Q6_K |
68
 
69
  Here is a handy graph by ikawrakow comparing some lower-quality quant