Qwen3.6-27B-Polaris-Heretic-mxfp8-mlx

Brainwaves

         arc   arc/e boolq hswag obkqa piqa  wino
mxfp8    0.673,0.846,0.905

Baseline model

         arc   arc/e boolq hswag obkqa piqa  wino
Qwen3.6-27B-Instruct
mxfp8    0.647,0.803,0.910,0.773,0.450,0.806,0.742
qx86-hi  0.637,0.798,0.911,0.775,0.442,0.807,0.737

This model Qwen3.6-27B-Polaris-Heretic-mxfp8-mlx was converted to MLX format from DavidAU/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking using mlx-lm version 0.31.3.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Qwen3.6-27B-Polaris-Heretic-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)