Instructions to use cyankiwi/Qwen3-Omni-30B-A3B-Thinking-AWQ-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cyankiwi/Qwen3-Omni-30B-A3B-Thinking-AWQ-8bit with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("cyankiwi/Qwen3-Omni-30B-A3B-Thinking-AWQ-8bit", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- e1245d1319f1ba4af0a40bd54f5ca48042c0f5bc27a243fadf399bfeff23c41b
- Size of remote file:
- 4.8 GB
- SHA256:
- 6ab3d11ade9522f0899a5beedd846c97623a3a6bd8bf7b35e5240cfe06a14785
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.