nightmedia

Qwen3.5-9B-TNG-PKD-Qwopus-Writer-Bradbury-F451-mxfp8-mlx

README

License: apache-2.0

Use with mlx

bash
pip install mlx-lm

python
from mlx_lm import load, generate

model, tokenizer = load("Qwen3.5-9B-TNG-PKD-Qwopus-Writer-Bradbury-F451-mxfp8-mlx")

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)