CoolFace
Modelpublic

mflux-community/qwen-image-mflux-q8

sourceHugging Faceapache-2.0updated 23h agoView on Hugging Face
0likes4.6kdownloads
Model Card

Qwen-Image · MFlux Q8

This is a Q8 MFlux version of **Qwen-Image-2512**.

**MFlux** runs the latest state-of-the-art generative image models locally on your Mac in native MLX. MFlux is open source and free.

[!NOTE] Community conversion by MFlux-Community -- not an official release from the original model's authors. The original model's license applies unchanged, see License.

MFlux versions of Qwen-Image-2512

QUANTGBRepo
BF1655.3mflux-community/qwen-image-mflux-bf16
Q836.1this repo
Q631.0mflux-community/qwen-image-mflux-q6
Q528.5mflux-community/qwen-image-mflux-q5
Q427.6mflux-community/qwen-image-mflux-q4
Q321.4mflux-community/qwen-image-mflux-q3

Converted on 2026-08-16.

Standard MFlux quantization uses MLX affine quantization (8-bit) across the text encoder, transformer and VAE. The quantization level is stored in the weights, so no --quantize flag is needed.

Usage

Install MFlux

bash
uv tool install --upgrade mflux

Generate an image using Qwen-Image-2512 Q8:

bash
mflux-generate-qwen \
  --model mflux-community/qwen-image-mflux-q8 \
  --base-model qwen-image \
  --prompt "A puffin standing on a cliff" \
  --width 1024 \
  --height 1024 \
  --seed 42 \
  --output image.png

The weights are downloaded from this repo on first use. To keep a local copy instead:

bash
hf download mflux-community/qwen-image-mflux-q8 --local-dir ./qwen-image-mflux-q8

then pass --model ./qwen-image-mflux-q8.

License

This repo inherits the license of the original model: apache-2.0. See the original model card for the full terms and any usage restrictions. The weights here were modified from the original release only by conversion to MLX and quantization.

Credits