Instructions to use OpensourceWTF/Qwen3.8-Flash-Next-MTPLX-oQ4-MTP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use OpensourceWTF/Qwen3.8-Flash-Next-MTPLX-oQ4-MTP with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen3.8-Flash-Next-MTPLX-oQ4-MTP OpensourceWTF/Qwen3.8-Flash-Next-MTPLX-oQ4-MTP
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
- Xet hash:
- c692ffe6ca5d62ba02fc7ccda953740fc6de23ea444b2fc7e4cfbf030555ad20
- Size of remote file:
- 5 GB
- SHA256:
- d760f4cec3a9b4b37ac2b6735722f6733a4879a1d0105b6ef8080a1772746d56
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.