Prompting

pip install -U mlx-lm
python -m mlx_lm.generate --model chenhunghan/TAIDE-LX-7B-Chat-mlx-4bit --prompt 'TAIDE可以吃嗎？'

Convert

python -m mlx_lm.convert --hf-path taide/TAIDE-LX-7B-Chat -q

Safetensors

Model size

1B params

Tensor type

F16

U32

MLX

Hardware compatibility

Quantized

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support