mradermacher commited on
Commit
1839885
·
verified ·
1 Parent(s): b1ccfa1

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -34,6 +34,7 @@ more details, including on how to concatenate multi-part files.
34
 
35
  | Link | Type | Size/GB | Notes |
36
  |:-----|:-----|--------:|:------|
 
37
  | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-IQ1_M.gguf) | i1-IQ1_M | 4.8 | mostly desperate |
38
  | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 5.1 | |
39
  | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 5.4 | |
@@ -41,14 +42,18 @@ more details, including on how to concatenate multi-part files.
41
  | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-IQ2_M.gguf) | i1-IQ2_M | 5.9 | |
42
  | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-Q2_K.gguf) | i1-Q2_K | 6.0 | IQ3_XXS probably better |
43
  | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.2 | lower quality |
 
 
44
  | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.9 | IQ3_XS probably better |
45
  | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-IQ3_M.gguf) | i1-IQ3_M | 7.2 | |
46
  | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.5 | IQ3_S probably better |
47
  | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 7.9 | IQ3_M probably better |
48
  | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 7.9 | |
 
49
  | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality |
50
  | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.3 | fast, recommended |
51
  | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.1 | |
 
52
  | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-Q6_K.gguf) | i1-Q6_K | 12.4 | practically like static Q6_K |
53
 
54
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
34
 
35
  | Link | Type | Size/GB | Notes |
36
  |:-----|:-----|--------:|:------|
37
+ | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-IQ1_S.gguf) | i1-IQ1_S | 4.6 | for the desperate |
38
  | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-IQ1_M.gguf) | i1-IQ1_M | 4.8 | mostly desperate |
39
  | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 5.1 | |
40
  | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 5.4 | |
 
42
  | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-IQ2_M.gguf) | i1-IQ2_M | 5.9 | |
43
  | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-Q2_K.gguf) | i1-Q2_K | 6.0 | IQ3_XXS probably better |
44
  | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.2 | lower quality |
45
+ | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.6 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-IQ3_S.gguf) | i1-IQ3_S | 6.9 | beats Q3_K* |
47
  | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.9 | IQ3_XS probably better |
48
  | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-IQ3_M.gguf) | i1-IQ3_M | 7.2 | |
49
  | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.5 | IQ3_S probably better |
50
  | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 7.9 | IQ3_M probably better |
51
  | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 7.9 | |
52
+ | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-Q4_0.gguf) | i1-Q4_0 | 8.3 | fast, low quality |
53
  | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality |
54
  | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.3 | fast, recommended |
55
  | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.1 | |
56
+ | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.6 | |
57
  | [GGUF](https://huggingface.co/mradermacher/Quyen-Pro-v0.1-i1-GGUF/resolve/main/Quyen-Pro-v0.1.i1-Q6_K.gguf) | i1-Q6_K | 12.4 | practically like static Q6_K |
58
 
59
  Here is a handy graph by ikawrakow comparing some lower-quality quant