Set up a local AI

Install a local model runner, download a model and verify that local inference works.

What this step is for.

A local model runner manages model downloads and exposes a way to run them on your computer. Ollama is one common option, but the workflow matters more than the brand: install a runner, obtain a model that fits your hardware, start it and verify a response.

Keep the scope small enough that you can inspect the result yourself. AI can accelerate the work, but it should not erase the distinction between a suggestion, a changed file, a successful build and a verified product.

Take one concrete action.

Install a trusted local model runner from its official source. Download one model appropriate for your hardware. Run a simple prompt, then restart the runner and confirm you can run the model again.

Turn the idea into evidence.

Do the action in a disposable or backed-up workspace first. Write down what you expected to happen, what actually happened and what you changed when the result differed. This small habit becomes increasingly important as your AI tools gain access to more files and commands.

Do not move on until this is true.

You can produce a local response after a restart and you know where the model files are stored.

Why we use this principle.

Nyfir Studios treats generated output and verified output as different states. Development work on local AI, Android software and bookkeeping workflows has repeatedly shown that recoverable state, explicit tests and clear product status are more useful than simply producing more output.