from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen2.5-7B-Instruct-4bit")
prompt = tokenizer.apply_chat_template(
    [{"role": "user", "content": "What is the Second Noble Truth?"}],
    tokenize=False, add_generation_prompt=True,
)
print(generate(model, tokenizer, prompt=prompt, max_tokens=200))