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-00001-of-00004.safetensors from ddalcu/Qwen-Image-2.1-MLX-Serve-4bit: direct link, hf CLI and curl.
- Browser
- Download file 2.5 GB
-
https://huggingface.co/ddalcu/Qwen-Image-2.1-MLX-Serve-4bit/resolve/main/text_encoder/model-00001-of-00004.safetensors
- Command line
-
hf download hf://ddalcu/Qwen-Image-2.1-MLX-Serve-4bit/text_encoder/model-00001-of-00004.safetensors
-
curl -L -o model-00001-of-00004.safetensors https://huggingface.co/ddalcu/Qwen-Image-2.1-MLX-Serve-4bit/resolve/main/text_encoder/model-00001-of-00004.safetensors
2.5 GB
- Xet hash:
- 2eb7246f31fa436ecc6cd97f313f93201815807a72aa6f380e30c3db6796b044
- Size of remote file:
- 2.5 GB
- SHA256:
- a34e4d4da153672997d985e0f481055f3c4f4e9bbddad412c93ff446be63c064
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.