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

          arc   arc/e boolq hswag obkqa piqa  wino
mxfp8     0.636,0.816,0.888

Quant     Perplexity      Peak Memory   Tokens/sec
mxfp8     4.218 ± 0.027   16.02 GB      687

          arc   arc/e boolq hswag obkqa piqa  wino
mxfp8     0.550,0.724,0.888,0.691,0.418,0.771,0.674
qx86-hi   0.556,0.718,0.885,0.701,0.432,0.776,0.684

          arc   arc/e boolq hswag obkqa piqa  wino
qx86-hi   0.642,0.819,0.895,0.716,0.454,0.785,0.699

models:
  - model: nightmedia/Qwen3.5-9B-TNG-PKD-Qwopus-Coder
    parameters:
      weight: 1.6
  - model: DavidAU/Qwen3.5-9B-The-Bradbury-F451-Pro-Writer-Uncensored-Heretic
    parameters:
      weight: 0.4
merge_method: nuslerp
dtype: bfloat16
name: Qwen3.5-9B-TNG-PKD-Qwopus-Writer-Bradbury-F451

pip install mlx-lm

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)