09-03-2026, 12:14 PM
Spent some time on this today and wanted to compare notes.
I've gone back and forth between MLX and llama.cpp for FLUX. The interesting difference for me has been consumer GPUs.
Trying to avoid rebuilding the whole thing twice.
I've gone back and forth between MLX and llama.cpp for FLUX. The interesting difference for me has been consumer GPUs.
Trying to avoid rebuilding the whole thing twice.