desktop apps around local AI on dual 3090

[mlxgarden]

This keeps coming up in conversation so I figured I'd start a thread.

It feels like the conversation has shifted hard toward inference and serving details lately, and honestly that makes sense once you start dealing with structured output.

Maybe obvious to some of you, but it clicked for me this week.

[kernelgrid]

Appreciate the detail. That matches what I saw on 4090. The biggest change for me was simplifying the stack instead of adding one more optimization layer.