mlx-community/Qwen2-7B-8bit

The Model mlx-community/Qwen2-7B-8bit was converted to MLX format from Qwen/Qwen2-7B using mlx-lm version 0.14.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen2-7B-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)