Hugging Face's logo

mradermacher
/
Qwen2.5-32B-Instruct-darija-i1-GGUF

Transformers
GGUF
Arabic
Moroccan Arabic
English
MoroccanArabic
Darija
GemMaroc
conversational
qwen
imatrix
Model card Files
xet
Community
mradermacher commited on
Commit
2b5c26f
·
verified ·
1 Parent(s): 672e6dc

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -0
README.md CHANGED
@@ -47,21 +47,28 @@ more details, including on how to concatenate multi-part files.
47
  | Link | Type | Size/GB | Notes |
48
  |:-----|:-----|--------:|:------|
49
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
 
50
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-IQ1_M.gguf) | i1-IQ1_M | 8.0 | mostly desperate |
51
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | |
52
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.1 | |
 
53
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-IQ2_M.gguf) | i1-IQ2_M | 11.4 | |
54
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.6 | very low quality |
55
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better |
56
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality |
 
57
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.5 | IQ3_XS probably better |
 
58
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-IQ3_M.gguf) | i1-IQ3_M | 14.9 | |
59
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.0 | IQ3_S probably better |
60
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.3 | IQ3_M probably better |
61
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.8 | |
 
62
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.9 | optimal size/speed/quality |
63
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.0 | fast, recommended |
 
64
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.7 | |
 
65
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.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
 
47
  | Link | Type | Size/GB | Notes |
48
  |:-----|:-----|--------:|:------|
49
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
50
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-IQ1_S.gguf) | i1-IQ1_S | 7.4 | for the desperate |
51
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-IQ1_M.gguf) | i1-IQ1_M | 8.0 | mostly desperate |
52
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | |
53
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.1 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-IQ2_S.gguf) | i1-IQ2_S | 10.5 | |
55
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-IQ2_M.gguf) | i1-IQ2_M | 11.4 | |
56
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.6 | very low quality |
57
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better |
58
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality |
59
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.8 | |
60
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.5 | IQ3_XS probably better |
61
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-IQ3_S.gguf) | i1-IQ3_S | 14.5 | beats Q3_K* |
62
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-IQ3_M.gguf) | i1-IQ3_M | 14.9 | |
63
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.0 | IQ3_S probably better |
64
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.3 | IQ3_M probably better |
65
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.8 | |
66
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-Q4_0.gguf) | i1-Q4_0 | 18.8 | fast, low quality |
67
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.9 | optimal size/speed/quality |
68
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.0 | fast, recommended |
69
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-Q4_1.gguf) | i1-Q4_1 | 20.7 | |
70
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.7 | |
71
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.4 | |
72
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-darija-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-darija.i1-Q6_K.gguf) | i1-Q6_K | 27.0 | practically like static Q6_K |
73
 
74
  Here is a handy graph by ikawrakow comparing some lower-quality quant