This is a BF16 MFlux version of Qwen-Image.
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.
| QUANT | GB | Repo |
|---|---|---|
| BF16 | 55.3 | this repo |
| Q8 | 36.1 | mflux-community/qwen-image-mflux-q8 |
| Q6 | 31.0 | mflux-community/qwen-image-mflux-q6 |
| Q5 | 28.5 | mflux-community/qwen-image-mflux-q5 |
| Q4 | 27.6 | mflux-community/qwen-image-mflux-q4 |
| Q3 | 23.4 | mflux-community/qwen-image-mflux-q3 |
Converted with MFlux 0.22.0 on 2026-10-11.
BF16 is the full-precision MLX build -- no quantization. Use it as the highest-fidelity reference, or pass --quantize to quantize on the fly.
Install MFlux
uv tool install --upgrade mflux
Generate an image using Qwen-Image BF16:
mflux-generate-qwen \
--model mflux-community/qwen-image-mflux-bf16 \
--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:
hf download mflux-community/qwen-image-mflux-bf16 --local-dir ./qwen-image-mflux-bf16
then pass --model ./qwen-image-mflux-bf16.
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.
Have the files? Submit a torrent.
Submit a torrentHave the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo mflux-community/qwen-image-mflux-bf16 ./model-foldertext_encoder/5.safetensors 2.1 GBtext_encoder/3.safetensors 2.1 GBtext_encoder/1.safetensors 2.1 GBtransformer/0.safetensors 2.1 GBtext_encoder/0.safetensors 2.1 GBtransformer/19.safetensors 2.1 GBtext_encoder/4.safetensors 2.1 GBtext_encoder/2.safetensors 2.1 GBtransformer/8.safetensors 2.0 GBtransformer/13.safetensors 2.0 GBtransformer/12.safetensors 2.0 GBtransformer/18.safetensors 2.0 GBtransformer/4.safetensors 2.0 GBtransformer/10.safetensors 2.0 GBtransformer/16.safetensors 2.0 GBtransformer/7.safetensors 2.0 GBtransformer/11.safetensors 2.0 GBtransformer/5.safetensors 2.0 GBtransformer/6.safetensors 2.0 GBtransformer/17.safetensors 2.0 GBtransformer/15.safetensors 2.0 GBtransformer/9.safetensors 2.0 GBtransformer/3.safetensors 2.0 GBtransformer/14.safetensors 2.0 GBtransformer/2.safetensors 2.0 GBtransformer/1.safetensors 2.0 GBtext_encoder/6.safetensors 1.5 GBvae/0.safetensors 254 MBQwen/Qwen-Image