Instructions to use vLLM-Kunlun/Qwen3-4B-Int8-Dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Adapters
How to use vLLM-Kunlun/Qwen3-4B-Int8-Dynamic with Adapters:
from adapters import AutoAdapterModel model = AutoAdapterModel.from_pretrained("undefined") model.load_adapter("vLLM-Kunlun/Qwen3-4B-Int8-Dynamic", set_active=True) - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- c48c2fbae2d7b3d18020a45fb3141aa7a63b164e16c17fe95aaf2890f0107069
- Size of remote file:
- 11.4 MB
- SHA256:
- 352a863cd2761388ccc58f1432467ba6a1037bf12df9069889b142fa246471f6
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.