mradermacher commited on
Commit
50b77a4
1 Parent(s): b44601e

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -0
README.md CHANGED
@@ -36,6 +36,7 @@ more details, including on how to concatenate multi-part files.
36
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.1 | |
37
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-IQ2_S.gguf) | i1-IQ2_S | 10.5 | |
38
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-IQ2_M.gguf) | i1-IQ2_M | 11.4 | |
 
39
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better |
40
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality |
41
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.8 | |
@@ -45,11 +46,18 @@ more details, including on how to concatenate multi-part files.
45
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.0 | IQ3_S probably better |
46
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.3 | IQ3_M probably better |
47
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.8 | |
 
 
 
 
48
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-Q4_0.gguf) | i1-Q4_0 | 18.8 | fast, low quality |
49
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.9 | optimal size/speed/quality |
50
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.0 | fast, recommended |
 
51
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.7 | |
 
52
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.4 | |
 
53
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-Q6_K.gguf) | i1-Q6_K | 27.0 | practically like static Q6_K |
54
 
55
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
36
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.1 | |
37
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-IQ2_S.gguf) | i1-IQ2_S | 10.5 | |
38
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-IQ2_M.gguf) | i1-IQ2_M | 11.4 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.6 | very low quality |
40
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better |
41
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality |
42
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.8 | |
 
46
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.0 | IQ3_S probably better |
47
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.3 | IQ3_M probably better |
48
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.8 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 18.7 | fast on arm, low quality |
50
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 18.7 | fast on arm+i8mm, low quality |
51
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 18.7 | fast on arm+sve, low quality |
52
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 18.8 | prefer IQ4_XS |
53
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-Q4_0.gguf) | i1-Q4_0 | 18.8 | fast, low quality |
54
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.9 | optimal size/speed/quality |
55
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.0 | fast, recommended |
56
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-Q4_1.gguf) | i1-Q4_1 | 20.7 | |
57
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.7 | |
58
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-Q5_0.gguf) | i1-Q5_0 | 22.8 | |
59
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.4 | |
60
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-Q5_1.gguf) | i1-Q5_1 | 24.7 | |
61
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-i1-GGUF/resolve/main/Qwen2.5-32B.i1-Q6_K.gguf) | i1-Q6_K | 27.0 | practically like static Q6_K |
62
 
63
  Here is a handy graph by ikawrakow comparing some lower-quality quant