Qwen3-Next-80B-A3B-Thinking-mlx-nvfp4

arthurcollet/Qwen3-Next-80B-A3B-Thinking-mlx-nvfp4

This model arthurcollet/Qwen3-Next-80B-A3B-Thinking-mlx-nvfp4 was converted to MLX format from Qwen/Qwen3-Next-80B-A3B-Thinking using mlx-lm version 0.30.7.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("arthurcollet/Qwen3-Next-80B-A3B-Thinking-mlx-nvfp4")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True, return_dict=False,
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)