Hugging Face's logo

nightmedia
/
QiMing-Moe-20B-MXFP4-qx86-hi-mlx

Text Generation
MLX
Safetensors
English
gpt_oss
unsloth
QiMing
vllm
conversational
4-bit precision
Model card Files
xet
Community
nightmedia commited on
Commit
c7864f7
·
verified ·
1 Parent(s): e619876

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -0
README.md CHANGED
@@ -14,6 +14,12 @@ base_model: aifeifei798/QiMing-Moe-20B-MXFP4
14
 
15
  # QiMing-Moe-20B-MXFP4-qx86-hi-mlx
16
 
 
 
 
 
 
 
17
  This model [QiMing-Moe-20B-MXFP4-qx86-hi-mlx](https://huggingface.co/QiMing-Moe-20B-MXFP4-qx86-hi-mlx) was
18
  converted to MLX format from [aifeifei798/QiMing-Moe-20B-MXFP4](https://huggingface.co/aifeifei798/QiMing-Moe-20B-MXFP4)
19
  using mlx-lm version **0.27.1**.
 
14
 
15
  # QiMing-Moe-20B-MXFP4-qx86-hi-mlx
16
 
17
+ This is just entertaining as a model and I got to see why...
18
+
19
+ Running some tests now.
20
+
21
+ -G
22
+
23
  This model [QiMing-Moe-20B-MXFP4-qx86-hi-mlx](https://huggingface.co/QiMing-Moe-20B-MXFP4-qx86-hi-mlx) was
24
  converted to MLX format from [aifeifei798/QiMing-Moe-20B-MXFP4](https://huggingface.co/aifeifei798/QiMing-Moe-20B-MXFP4)
25
  using mlx-lm version **0.27.1**.