          arc   arc/e boolq hswag obkqa piqa  wino
qx86-hi   0.434,0.485,0.380

Instruct
qx86-hi   0.653,0.810,0.901,0.744,0.440,0.799,0.723

Quant     Perplexity      Peak Memory   Tokens/sec
qx86-hi   3.818 ± 0.024   32.36 GB      139

Baseline model

brainwaves

Qwen3.5-27B
          arc   arc/e boolq hswag obkqa piqa  wino
qx86-hi   0.443,0.498,0.857,0.701,0.372,0.770,0.752

Use with mlx

pip install mlx-lm

python

from mlx_lm import load, generate

model, tokenizer = load("Qwopus3.5-27B-v3.5-qx86-hi-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)

nightmedia/Qwopus3.5-27B-v3.5-qx86-hi-mlx

Qwopus3.5-27B-v3.5-qx86-hi-mlx

Baseline model

Use with mlx

nightmedia/
Qwopus3.5-27B-v3.5-qx86-hi-mlx