Hugging Face's logo

mradermacher
/
Qwen2.5-3B-i1-GGUF

Transformers
GGUF
English
Inference Endpoints
imatrix
conversational
Model card Files Community
mradermacher commited on
Commit
53cc670
•
1 Parent(s): e5b8e5c

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -33,6 +33,7 @@ more details, including on how to concatenate multi-part files.
33
  |:-----|:-----|--------:|:------|
34
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-i1-GGUF/resolve/main/Qwen2.5-3B.i1-Q2_K.gguf) | i1-Q2_K | 1.4 | IQ3_XXS probably better |
35
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-i1-GGUF/resolve/main/Qwen2.5-3B.i1-IQ3_M.gguf) | i1-IQ3_M | 1.6 | |
 
36
 
37
  Here is a handy graph by ikawrakow comparing some lower-quality quant
38
  types (lower is better):
 
33
  |:-----|:-----|--------:|:------|
34
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-i1-GGUF/resolve/main/Qwen2.5-3B.i1-Q2_K.gguf) | i1-Q2_K | 1.4 | IQ3_XXS probably better |
35
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-i1-GGUF/resolve/main/Qwen2.5-3B.i1-IQ3_M.gguf) | i1-IQ3_M | 1.6 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-i1-GGUF/resolve/main/Qwen2.5-3B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.9 | optimal size/speed/quality |
37
 
38
  Here is a handy graph by ikawrakow comparing some lower-quality quant
39
  types (lower is better):