100% free open-source MLX implementation by filipstrand for running FLUX.1 and FLUX.2 image models locally on Apple Silicon Mac computers.
Yes (100% free open-source software running locally on Apple Silicon Mac hardware in India)mflux (by filipstrand) is a 100% free and open-source Python implementation built specifically for Apple Silicon (M1/M2/M3/M4) Mac computers. Powered by Apple's MLX machine learning framework, mflux enables Mac users to run heavy FLUX.1 [schnell] and FLUX.1 [dev] 12-billion parameter models natively on Mac GPUs with optimal memory efficiency, quantized 4-bit weights, and zero cloud API fees.
No reviews yet โ be the first to review!
mflux is a 100% free open-source MLX implementation for running FLUX image models natively on Apple Silicon Macs.
Yes, mflux is 100% free and open-source with zero subscription fees or generation limits.
Yes, it installs and runs locally on Apple Silicon Mac computers in India.
mflux is exclusive to Apple Silicon Mac computers (M1/M2/M3/M4 chips running macOS).
A Mac with 16GB+ Unified Memory is recommended for running 4-bit quantized FLUX.1 models.
Yes, once model weights are cached, mflux operates completely offline on your Mac.