Transformers How to use nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-FP8 with Transformers:
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-FP8", trust_remote_code=True, device_map="auto") 
