Local AI Is Good Enough Now: Here Is What We Run Daily

For a long time the honest answer about local AI was “impressive, but not yet.” It ran, it just was not good enough to replace the tools you actually relied on. That sentence quietly stopped being true. For the work most of us do every day, a model on your own machine is now good enough, and the proof is not a benchmark. It is what we run.

So here is what the studio actually uses, every day, with nothing leaving the building.

The foundation

Ollama is on every machine. It is the first thing we install and the engine everything else plugs into. One command pulls a model, and it serves that model locally so every other tool can reach it. There is no version of our day that does not touch it.

The coding work

OpenCode, the desktop app, pointed at a local model through Ollama. It reads our files, edits them, and runs commands in a normal app window, and it keeps working with the Wi-Fi off. This is the one that surprised us most. We expected to keep a cloud agent for “real” work and use local for toys. Instead the local setup carried the daily load, and the cloud became the exception we reach for only on genuinely hard problems.

The everyday questions

A local chat on top of Ollama handles drafting, rewriting, quick reasoning, and the hundred small questions a workday produces. None of it is sensitive enough to send anywhere, and now none of it has to be.

When speed matters

For jobs that grind, batch transcription, evaluation runs, anything long, we switch to MLX, Apple’s framework, which runs faster on the same Mac. Convenience by default, speed when the clock is the bottleneck.

The honest caveat

Good enough is not the same as best. On the hardest problems, a frontier cloud model is still ahead, and we will not pretend otherwise. If your work lives at that frontier all day, keep the cloud tool that earns it.

But “the hardest problems all day” is not most people’s work, and it is not most of ours. Most work is ordinary, and ordinary is exactly what a local model handles now. The bar moved. The question stopped being “can it run locally” and became “is it good enough,” and for daily work the answer turned to yes.

The way to know is not to read another comparison. It is to run the local version of something you do every day and notice that you did not miss the cloud. That is the whole shift, and you can test it this afternoon.

Curious about these things. You should be too.