mlx-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-mxfp4
This model mlx-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-mxfp4 was converted to MLX format from nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 using mlx-lm version 0.31.3 (MXFP4, group size 32).
NVIDIA-Nemotron-3.5-Lightning-30B-A3B is a hybrid Mamba-2 / attention Mixture-of-Experts model (~31B total parameters, ~3B active per token).
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-mxfp4")
prompt = "Hello, who are you?"
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)