Qwen-Image-mflux-4bit

4-bit quantized weights for the Qwen-Image model compatible with MFLUX.

About

4bit qunatized weights for the Qwen Image model compatible with MFLUX.

Requires MFLUX v0.11.0 or later to run. For more information, visit https://github.com/filipstrand/mflux

Installation

To use this model, you need MFLUX installed:

uv tool install --upgrade mflux

Usage

Once installed, generate images with:

mflux-generate \
    --model carsenk/qwen-image-mflux-4bit \
    --prompt "A photo of a serene mountain landscape at sunset" \
    --steps 25 \
    --seed 42

Model Details

Quantization: 4-bit
Framework: MFLUX
Compatible with: MFLUX v0.11.0 or later
Architecture: Qwen-Image

License

This model inherits the license of the original Qwen model. Please refer to the original model repository for detailed licensing information.

Downloads last month: -; Downloads are not tracked for this model. How to track