MiroThinker-v1.0-30B-Terminus-qx86-hi-mlx

MiroThinker-v1.0-30B-qx86-hi         ,0.441,0.494,0.758,0.664,0.412,0.774,0.690
MiroThinker-v1.0-30B-Terminus-qx86-hi,0.418,0.450,0.633,0.638,0.400,0.776,0.663

..oh well :)

This model MiroThinker-v1.0-30B-Terminus-qx86-hi-mlx was converted to MLX format from miromind-ai/MiroThinker-v1.0-30B-Terminus using mlx-lm version 0.30.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("MiroThinker-v1.0-30B-Terminus-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)