workflow automation with local models on dual 3090

[labline]

A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with Llama and compare from there. A lot of these threads end

A couple things I'd check first. If you're on MLX, I'd confirm the version first and then reduce variables until the behavior is obvious. Once you know the plain path works, then add the faster path back in piece by piece.