Magidonia-24B-v4.2.0-qx86-hi-mlx

Perplexity: 4.781 ± 0.035
Peak memory: 26.18 GB

Detailed metrics coming soon.

-G

This model Magidonia-24B-v4.2.0-qx86-hi-mlx was converted to MLX format from TheDrummer/Magidonia-24B-v4.2.0 using mlx-lm version 0.28.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Magidonia-24B-v4.2.0-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
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)