Instructions to use ddalcu/Qwen-Image-2.1-MLX-Serve-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use ddalcu/Qwen-Image-2.1-MLX-Serve-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen-Image-2.1-MLX-Serve-4bit ddalcu/Qwen-Image-2.1-MLX-Serve-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download text_encoder/model-00004-of-00004.safetensors from ddalcu/Qwen-Image-2.1-MLX-Serve-4bit: direct link, hf CLI and curl.
- Browser
- Download file 411 MB
-
https://huggingface.co/ddalcu/Qwen-Image-2.1-MLX-Serve-4bit/resolve/main/text_encoder/model-00004-of-00004.safetensors
- Command line
-
hf download hf://ddalcu/Qwen-Image-2.1-MLX-Serve-4bit/text_encoder/model-00004-of-00004.safetensors
-
curl -L -o model-00004-of-00004.safetensors https://huggingface.co/ddalcu/Qwen-Image-2.1-MLX-Serve-4bit/resolve/main/text_encoder/model-00004-of-00004.safetensors
411 MB
- Xet hash:
- ae63079556f34150468442960b77a973975168fe1958db231aff597cbd17adb3
- Size of remote file:
- 411 MB
- SHA256:
- 98b02a3ef8de4da20df504bf8804854e601797bf8c0a56a7730baf84b07d165e
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.