Hugging Face's logo

mradermacher
/
Apertus-AlphaPO-5e-6-8B-i1-GGUF

Transformers
GGUF
English
text-generation-inference
unsloth
apertus
trl
cpo
imatrix
conversational
Model card Files
xet
Community
mradermacher commited on
Commit
4ec016f
·
verified ·
1 Parent(s): db4ee76

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md CHANGED
@@ -45,20 +45,29 @@ more details, including on how to concatenate multi-part files.
45
  | Link | Type | Size/GB | Notes |
46
  |:-----|:-----|--------:|:------|
47
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
 
48
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate |
49
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | |
 
 
50
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-IQ2_M.gguf) | i1-IQ2_M | 3.1 | |
51
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality |
52
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality |
53
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-Q2_K.gguf) | i1-Q2_K | 3.4 | IQ3_XXS probably better |
 
54
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better |
 
55
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | |
56
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.3 | IQ3_S probably better |
57
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.6 | |
58
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.7 | IQ3_M probably better |
59
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS |
 
60
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality |
61
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.2 | fast, recommended |
 
 
 
62
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K |
63
 
64
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
45
  | Link | Type | Size/GB | Notes |
46
  |:-----|:-----|--------:|:------|
47
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
48
+ | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate |
49
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate |
50
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | |
52
+ | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | |
53
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-IQ2_M.gguf) | i1-IQ2_M | 3.1 | |
54
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality |
55
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality |
56
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-Q2_K.gguf) | i1-Q2_K | 3.4 | IQ3_XXS probably better |
57
+ | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.7 | |
58
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better |
59
+ | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* |
60
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | |
61
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.3 | IQ3_S probably better |
62
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.6 | |
63
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.7 | IQ3_M probably better |
64
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS |
65
+ | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality |
66
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality |
67
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.2 | fast, recommended |
68
+ | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | |
69
+ | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | |
70
+ | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.9 | |
71
  | [GGUF](https://huggingface.co/mradermacher/Apertus-AlphaPO-5e-6-8B-i1-GGUF/resolve/main/Apertus-AlphaPO-5e-6-8B.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K |
72
 
73
  Here is a handy graph by ikawrakow comparing some lower-quality quant