Modelpublic

moona3k/mlx-qwen3-asr-0.6b-4bit

sourceHugging Faceapache-2.0updated 8d agoView on Hugging Face

0likes41downloads

2 commits on main

4c59c538d ago

Add 4bit (g64) MLX weights from Qwen/Qwen3-ASR-0.6B, validated with mlx-qwen3-asr 0.4.3

moona3k

d9844108d ago

initial commit

moona3k