metadata
license: apache-2.0
library_name: mlx
tags:
- language
- granite-4.1
- mlx
pipeline_tag: text-generation
base_model: ibm-granite/granite-4.1-8b
mlx-community/granite-4.1-8b-8bit
This model mlx-community/granite-4.1-8b-8bit was converted to MLX format from ibm-granite/granite-4.1-8b using mlx-lm version 0.31.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/granite-4.1-8b-8bit")
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)