JanusCoder-8B-Claude-Opus-qx86-hi-mlx

This model is a merge of

• unsloth/JanusCoder-8B
• TeichAI/Qwen3-8B-Claude-4.5-Opus-High-Reasoning-Distill

Perplexity
qx86-hi   4.339 ± 0.031
qx64-hi   4.430 ± 0.032

Metrics coming soon.

-G

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("JanusCoder-8B-Claude-Opus-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)