Instructions to use yunfengwang/zimgturbo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use yunfengwang/zimgturbo with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir zimgturbo yunfengwang/zimgturbo
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
zimgturbo weights (int8)
int8-quantized Z-Image-Turbo for the zimgturbo engine
on Apple Silicon. Derived from Tongyi-MAI/Z-Image-Turbo.
uvx zimgturbo setup # pulls this bundle
uvx zimgturbo "a cat on a windowsill" -o cat.png
Contents: weights.bin/weights.idx (int8 DiT), text_encoder_int8.safetensors (int8 Qwen3),
vae.safetensors+vae_config.json (fp16 VAE), text_encoder/config.json, tokenizer/.
Hardware compatibility
Log In to add your hardware
Quantized
Model tree for yunfengwang/zimgturbo
Base model
Tongyi-MAI/Z-Image-Turbo