license, license_link, language, base_model, pipeline_tag, tags, inference, widget, library_name

license	license_link	language	base_model	pipeline_tag	tags	inference	widget	library_name
mit	https://huggingface.co/microsoft/Phi-4-reasoning-plus/resolve/main/LICENSE	en	microsoft/Phi-4-reasoning-plus	text-generation	phi nlp math code chat conversational reasoning mlx	parameters temperature 0	messages role content user What is the derivative of x^2?	mlx

mlx-community/Phi-4-reasoning-plus-bf16

This model mlx-community/Phi-4-reasoning-plus-bf16 was converted to MLX format from microsoft/Phi-4-reasoning-plus using mlx-lm version 0.23.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Phi-4-reasoning-plus-bf16")

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)