Any-to-Any
Transformers
Safetensors
English
Chinese
qwen3_omni_moe
text-to-audio
multimodal
fp8
quantization
compressed-tensors
vllm
Instructions to use tturing/Qwen3-Omni-30B-A3B-Thinking-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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") - Notebooks
- Google Colab
- Kaggle
Ctrl+K