LittleLamb-mxfp8-mlx

LittleLamb-mxfp8-mlx

Brainwaves

         arc   arc/e boolq hswag obkqa piqa  wino
LittleLamb
mxfp8    0.309,0.393,0.431,0.372,0.340,0.625,0.553
LittleLamb-ToolCalling
mxfp8    0.288,0.370,0.424,0.364,0.334,0.626,0.543

Qwen3-0.6B
bf16     0.298,0.354,0.378,0.415,0.344,0.649,0.534
q8-hi    0.296,0.355,0.378,0.416,0.348,0.652,0.529

This model LittleLamb-mxfp8-mlx was converted to MLX format from MultiverseComputingCAI/LittleLamb using mlx-lm version 0.31.3.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("LittleLamb-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)