10-03-2026, 04:04 PM
Spent some time on this today and wanted to compare notes.
I've gone back and forth between llama.cpp and MLX for FLUX. The interesting difference for me has been small local stacks.
Interested in tradeoffs more than fan loyalty.
This is mostly for local work rather than public serving.
I've gone back and forth between llama.cpp and MLX for FLUX. The interesting difference for me has been small local stacks.
Interested in tradeoffs more than fan loyalty.
This is mostly for local work rather than public serving.
measure twice, benchmark three times