Granite 4.1
Collection
By IBM • 8 items • Updated • 2
This model mlx-community/granite-4.1-3b-mxfp8 was converted to MLX format from ibm-granite/granite-4.1-3b using mlx-lm version 0.31.3.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/granite-4.1-3b-mxfp8")
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)
8-bit
Base model
ibm-granite/granite-4.1-3b