Initial upload: 8-bit quantized Vidi1.5-9B for MLX f5d508f
wangjazz commited on
How to use wangjazz/Vidi1.5-9B-mlx-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Vidi1.5-9B-mlx-8bit wangjazz/Vidi1.5-9B-mlx-8bit