Hugging Face's logo

mradermacher
/
Qwen2.5-72B-Instruct-i1-GGUF

Transformers
GGUF
English
chat
Inference Endpoints
imatrix
conversational
Model card Files Community
mradermacher commited on
Commit
0ce5144
·
verified ·
1 Parent(s): c079a72

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -0
README.md CHANGED
@@ -39,6 +39,7 @@ more details, including on how to concatenate multi-part files.
39
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 27.2 | |
40
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 28.0 | |
41
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 29.4 | |
 
42
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 29.9 | IQ3_XXS probably better |
43
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 31.9 | lower quality |
44
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 32.9 | |
@@ -48,11 +49,18 @@ more details, including on how to concatenate multi-part files.
48
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 37.8 | IQ3_S probably better |
49
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 39.6 | IQ3_M probably better |
50
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 39.8 | |
 
 
 
 
51
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 41.5 | fast, low quality |
52
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 44.0 | optimal size/speed/quality |
 
53
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 47.5 | fast, recommended |
 
54
  | [PART 1](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q5_K_S.gguf.part2of2) | i1-Q5_K_S | 51.5 | |
55
  | [PART 1](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 54.5 | |
 
56
  | [PART 1](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 64.4 | practically like static Q6_K |
57
 
58
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
39
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 27.2 | |
40
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 28.0 | |
41
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 29.4 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 29.7 | very low quality |
43
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 29.9 | IQ3_XXS probably better |
44
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 31.9 | lower quality |
45
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 32.9 | |
 
49
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 37.8 | IQ3_S probably better |
50
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 39.6 | IQ3_M probably better |
51
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 39.8 | |
52
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 41.3 | fast on arm, low quality |
53
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 41.3 | fast on arm+i8mm, low quality |
54
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 41.3 | fast on arm+sve, low quality |
55
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-IQ4_NL.gguf) | i1-IQ4_NL | 41.4 | prefer IQ4_XS |
56
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 41.5 | fast, low quality |
57
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 44.0 | optimal size/speed/quality |
58
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q4_1.gguf) | i1-Q4_1 | 45.8 | |
59
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 47.5 | fast, recommended |
60
+ | [PART 1](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q5_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q5_0.gguf.part2of2) | i1-Q5_0 | 50.4 | |
61
  | [PART 1](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q5_K_S.gguf.part2of2) | i1-Q5_K_S | 51.5 | |
62
  | [PART 1](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 54.5 | |
63
+ | [PART 1](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q5_1.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q5_1.gguf.part2of2) | i1-Q5_1 | 54.7 | |
64
  | [PART 1](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-i1-GGUF/resolve/main/Qwen2.5-72B-Instruct.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 64.4 | practically like static Q6_K |
65
 
66
  Here is a handy graph by ikawrakow comparing some lower-quality quant