Hugging Face's logo

mradermacher
/
Stable-DiffCoder-8B-Base-i1-GGUF

Transformers
GGUF
English
imatrix
Model card Files
xet
Community
mradermacher commited on
Commit
0b3e2ab
·
verified ·
1 Parent(s): 54ac9be

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md CHANGED
@@ -38,20 +38,29 @@ more details, including on how to concatenate multi-part files.
38
  | Link | Type | Size/GB | Notes |
39
  |:-----|:-----|--------:|:------|
40
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) |
 
41
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-IQ1_M.gguf) | i1-IQ1_M | 2.4 | mostly desperate |
42
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.6 | |
 
 
43
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-IQ2_M.gguf) | i1-IQ2_M | 3.2 | |
44
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.2 | very low quality |
45
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-Q2_K.gguf) | i1-Q2_K | 3.4 | IQ3_XXS probably better |
46
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.5 | lower quality |
 
47
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.9 | IQ3_XS probably better |
 
48
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-IQ3_M.gguf) | i1-IQ3_M | 4.0 | |
49
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.3 | IQ3_S probably better |
50
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.6 | IQ3_M probably better |
51
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.7 | |
 
52
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.9 | prefer IQ4_XS |
53
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.9 | optimal size/speed/quality |
54
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.2 | fast, recommended |
 
 
 
55
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-Q6_K.gguf) | i1-Q6_K | 6.9 | practically like static Q6_K |
56
 
57
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
38
  | Link | Type | Size/GB | Notes |
39
  |:-----|:-----|--------:|:------|
40
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) |
41
+ | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-IQ1_S.gguf) | i1-IQ1_S | 2.2 | for the desperate |
42
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-IQ1_M.gguf) | i1-IQ1_M | 2.4 | mostly desperate |
43
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.6 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.8 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-IQ2_S.gguf) | i1-IQ2_S | 3.0 | |
46
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-IQ2_M.gguf) | i1-IQ2_M | 3.2 | |
47
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.2 | very low quality |
48
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-Q2_K.gguf) | i1-Q2_K | 3.4 | IQ3_XXS probably better |
49
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.5 | lower quality |
50
+ | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.8 | |
51
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.9 | IQ3_XS probably better |
52
+ | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-IQ3_S.gguf) | i1-IQ3_S | 3.9 | beats Q3_K* |
53
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-IQ3_M.gguf) | i1-IQ3_M | 4.0 | |
54
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.3 | IQ3_S probably better |
55
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.6 | IQ3_M probably better |
56
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.7 | |
57
+ | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-Q4_0.gguf) | i1-Q4_0 | 4.9 | fast, low quality |
58
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.9 | prefer IQ4_XS |
59
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.9 | optimal size/speed/quality |
60
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.2 | fast, recommended |
61
+ | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-Q4_1.gguf) | i1-Q4_1 | 5.4 | |
62
+ | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.9 | |
63
+ | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-Q5_K_M.gguf) | i1-Q5_K_M | 6.0 | |
64
  | [GGUF](https://huggingface.co/mradermacher/Stable-DiffCoder-8B-Base-i1-GGUF/resolve/main/Stable-DiffCoder-8B-Base.i1-Q6_K.gguf) | i1-Q6_K | 6.9 | practically like static Q6_K |
65
 
66
  Here is a handy graph by ikawrakow comparing some lower-quality quant