mradermacher commited on
Commit
0d74fcb
1 Parent(s): e572289

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -1
README.md CHANGED
@@ -19,7 +19,6 @@ tags:
19
  weighted/imatrix quants of https://huggingface.co/Qwen/Qwen2.5-7B-Instruct
20
 
21
  <!-- provided-files -->
22
- static quants are available at https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-GGUF
23
  ## Usage
24
 
25
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -38,6 +37,7 @@ more details, including on how to concatenate multi-part files.
38
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | |
39
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 2.7 | |
40
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 2.9 | |
 
41
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 3.1 | IQ3_XXS probably better |
42
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.2 | lower quality |
43
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.4 | |
@@ -50,11 +50,15 @@ more details, including on how to concatenate multi-part files.
50
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.5 | fast on arm, low quality |
51
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.5 | fast on arm+i8mm, low quality |
52
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.5 | fast on arm+sve, low quality |
 
53
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 4.5 | fast, low quality |
54
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality |
55
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.8 | fast, recommended |
 
56
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.4 | |
 
57
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.5 | |
 
58
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-Q6_K.gguf) | i1-Q6_K | 6.4 | practically like static Q6_K |
59
 
60
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
19
  weighted/imatrix quants of https://huggingface.co/Qwen/Qwen2.5-7B-Instruct
20
 
21
  <!-- provided-files -->
 
22
  ## Usage
23
 
24
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
37
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | |
38
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 2.7 | |
39
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 2.9 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.9 | very low quality |
41
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 3.1 | IQ3_XXS probably better |
42
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.2 | lower quality |
43
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.4 | |
 
50
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.5 | fast on arm, low quality |
51
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.5 | fast on arm+i8mm, low quality |
52
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.5 | fast on arm+sve, low quality |
53
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.5 | prefer IQ4_XS |
54
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 4.5 | fast, low quality |
55
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality |
56
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.8 | fast, recommended |
57
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-Q4_1.gguf) | i1-Q4_1 | 5.0 | |
58
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.4 | |
59
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-Q5_0.gguf) | i1-Q5_0 | 5.4 | |
60
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.5 | |
61
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-Q5_1.gguf) | i1-Q5_1 | 5.9 | |
62
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct.i1-Q6_K.gguf) | i1-Q6_K | 6.4 | practically like static Q6_K |
63
 
64
  Here is a handy graph by ikawrakow comparing some lower-quality quant