Hugging Peers

Qwen3-Coder-Next-4bit

☆ Save
by async0x42 text-generation mlx apache-2.0
79 downloads 1 likes on Hugging Face updated

Model card

async0x42/Qwen3-Coder-Next-4bit

This model async0x42/Qwen3-Coder-Next-4bit was converted to MLX format from unsloth/Qwen3-Coder-Next using mlx-lm version 0.30.7.

Use with mlx

pip install mlx-lm



from mlx_lm import load, generate

model, tokenizer = load("async0x42/Qwen3-Coder-Next-4bit")

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)