Hugging Face's logo

anemll
/
anemll-Qwen3-4B-ctx1024_0.3.0

Core ML
llama
ANE
Qwen
Apple
Apple Neural Engine
Model card Files
xet
 Community
1
anemll commited on
Commit
c177a09
·
verified ·
1 Parent(s): 167ee10

Update meta.yaml

Browse files
Files changed (1) hide show
  1. meta.yaml +1 -1
meta.yaml CHANGED
@@ -2,7 +2,7 @@ model_info:
2
  name: anemll-Qwen3-4B-MLX-dequantized-ctx1024
3
  version: 0.1.1
4
  description: |
5
- Demonstarates running Qwen3-4B-MLX-dequantized on Apple Neural Engine
6
  Context length: 1024
7
  Batch size: 64
8
  Chunks: 2
 
2
  name: anemll-Qwen3-4B-MLX-dequantized-ctx1024
3
  version: 0.1.1
4
  description: |
5
+ Demonstarates running Qwen3-4B on Apple Neural Engine ( alpha release )
6
  Context length: 1024
7
  Batch size: 64
8
  Chunks: 2