Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-mlx_8bit

WaveCut/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-mlx_8bit

This model WaveCut/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-mlx_8bit was converted to MLX format from Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled using mlx-lm version 0.30.7.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("WaveCut/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-mlx_8bit")

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)