nightmedia/gemma-4-12B-coder-fable5-composer2.5-v1-uncensored-heretic-mxfp8-mlx

🤗 Hugging Face sourceany-to-anyapache-2.012B params24 GBsafetensors✓ 4 checksumsupdated today

Submit in one command

Run it next to your model folder. It makes the torrent, checks your files against Hugging Face, and submits it. You just start seeding and paste your key from your account. It only reads your files and never changes them. Read the script first if you like.

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo nightmedia/gemma-4-12B-coder-fable5-composer2.5-v1-uncensored-heretic-mxfp8-mlx ./model-folder

Needs a seeder →

gemma-4-12B-coder-fable5-composer2.5-v1-uncensored-heretic-mxfp8-mlx

Brainwaves

         arc   arc/e boolq hswag obkqa piqa  wino
mxfp8    0.421,0.546,0.758,0.530,0.380,0.712,0.596

Quant    Perplexity      Peak Memory   Tokens/sec
mxfp8   339.868 ± 6.406  18.27 GB      326

Original model

yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1

         arc   arc/e boolq hswag obkqa piqa  wino
mxfp8    0.422,0.549,0.754,0.537,0.388,0.717,0.611

Quant    Perplexity      Peak Memory   Tokens/sec
mxfp8   292.901 ± 5.389  18.27 GB      330

Baseline model

google/gemma-4-12B-it

         arc   arc/e boolq hswag obkqa piqa  wino
mxfp8    0.385,0.527,0.766,0.509,0.386,0.664,0.579

Quant    Perplexity      Peak Memory   Tokens/sec
mxfp8   175.766 ± 3.092  19.42 GB      463

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("gemma-4-12B-coder-fable5-composer2.5-v1-uncensored-heretic-mxfp8-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)