Hugging Face's logo

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

Transformers
GGUF
English
chat
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
0f097b6
·
verified ·
1 Parent(s): 670af5a

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -35,8 +35,11 @@ more details, including on how to concatenate multi-part files.
35
  |:-----|:-----|--------:|:------|
36
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-GGUF/resolve/main/Qwen2.5-72B-Instruct.Q2_K.gguf) | Q2_K | 29.9 | |
37
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-GGUF/resolve/main/Qwen2.5-72B-Instruct.IQ3_S.gguf) | IQ3_S | 34.6 | beats Q3_K* |
 
38
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-GGUF/resolve/main/Qwen2.5-72B-Instruct.IQ3_M.gguf) | IQ3_M | 35.6 | |
 
39
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-GGUF/resolve/main/Qwen2.5-72B-Instruct.Q4_K_S.gguf) | Q4_K_S | 44.0 | fast, recommended |
 
40
  | [PART 1](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-GGUF/resolve/main/Qwen2.5-72B-Instruct.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-GGUF/resolve/main/Qwen2.5-72B-Instruct.Q8_0.gguf.part2of2) | Q8_0 | 77.4 | fast, best quality |
41
 
42
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
35
  |:-----|:-----|--------:|:------|
36
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-GGUF/resolve/main/Qwen2.5-72B-Instruct.Q2_K.gguf) | Q2_K | 29.9 | |
37
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-GGUF/resolve/main/Qwen2.5-72B-Instruct.IQ3_S.gguf) | IQ3_S | 34.6 | beats Q3_K* |
38
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-GGUF/resolve/main/Qwen2.5-72B-Instruct.Q3_K_S.gguf) | Q3_K_S | 34.6 | |
39
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-GGUF/resolve/main/Qwen2.5-72B-Instruct.IQ3_M.gguf) | IQ3_M | 35.6 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-GGUF/resolve/main/Qwen2.5-72B-Instruct.Q3_K_M.gguf) | Q3_K_M | 37.8 | lower quality |
41
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-GGUF/resolve/main/Qwen2.5-72B-Instruct.Q4_K_S.gguf) | Q4_K_S | 44.0 | fast, recommended |
42
+ | [PART 1](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-GGUF/resolve/main/Qwen2.5-72B-Instruct.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-GGUF/resolve/main/Qwen2.5-72B-Instruct.Q6_K.gguf.part2of2) | Q6_K | 64.4 | very good quality |
43
  | [PART 1](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-GGUF/resolve/main/Qwen2.5-72B-Instruct.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-72B-Instruct-GGUF/resolve/main/Qwen2.5-72B-Instruct.Q8_0.gguf.part2of2) | Q8_0 | 77.4 | fast, best quality |
44
 
45
  Here is a handy graph by ikawrakow comparing some lower-quality quant