Mistral-Nemo-2407-12B-IT-Claude-Opus-250x-qx86-hi-mlx

Brainwaves

this model  0.503,0.722,0.873,0.762,0.464,0.801,0.725
baseline    0.516,0.743,0.862,0.720,0.464,0.794,0.696

This model Mistral-Nemo-2407-12B-IT-Claude-Opus-250x-qx86-hi-mlx was converted to MLX format from DavidAU/2B-MN-INST-R256-claude-opus-4.5-250x-cp60 using mlx-lm version 0.30.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Mistral-Nemo-2407-12B-IT-Claude-Opus-250x-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)