nightmedia/Qwen3.5-9B-TNG-PKD-Qwopus-Writer-Orwell-1984-mxfp8-mlx

          arc   arc/e boolq hswag obkqa piqa  wino
mxfp8     0.642,0.811,0.887

Quant     Perplexity      Peak Memory   Tokens/sec
mxfp8     4.298 ± 0.028   16.02 GB      630

          arc   arc/e boolq hswag obkqa piqa  wino
qx86-hi   0.575,0.738,0.880

          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-Pro-Writer-1984-Orwell-Uncensored-Heretic
    parameters:
      weight: 0.4
merge_method: nuslerp
dtype: bfloat16
name: Qwen3.5-9B-TNG-PKD-Qwopus-Writer-Orwell-1984

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Qwen3.5-9B-TNG-PKD-Qwopus-Writer-Orwell-1984-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)