mlx-community/Qwen1.5-32B-Chat-8bit

This model was converted to MLX format from Qwen/Qwen1.5-32B-Chat. Refer to the original model card for more details on the model.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen1.5-32B-Chat-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)