How to use tturing/Qwen3-Omni-30B-A3B-Thinking-FP8 with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("tturing/Qwen3-Omni-30B-A3B-Thinking-FP8") model = AutoModelForMultimodalLM.from_pretrained("tturing/Qwen3-Omni-30B-A3B-Thinking-FP8", device_map="auto")
