arc   arc/e boolq hswag obkqa piqa  wino
mxfp8    0.503,0.640,0.861

Quant    Perplexity      Peak Memory   Tokens/sec
mxfp8    4.685 ± 0.033   12.17 GB      563

Base model

granite-4.1-8b
         arc   arc/e boolq hswag obkqa piqa  wino
mxfp8    0.486,0.666,0.875,0.636,0.450,0.766,0.631

Quant    Perplexity      Peak Memory   Tokens/sec
mxfp8   10.134 ± 0.107   12.17 GB      286

More metrics coming soon.

-G

granite-4.1-8b-Stone-Cold-Thinking-V1-mxfp8-mlx

This model granite-4.1-8b-Stone-Cold-Thinking-V1-mxfp8-mlx was converted to MLX format from DavidAU/granite-4.1-8b-Stone-Cold-Thinking using mlx-lm version 0.31.3.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("granite-4.1-8b-Stone-Cold-Thinking-V1-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)