mlx-community/granite-4.0-350m-bf16

This model mlx-community/granite-4.0-350m-bf16 was converted to MLX format from ibm-granite/granite-4.0-350m using mlx-lm version 0.28.4.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/granite-4.0-350m-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)