Choose a model that fits
Start from the task
Choose a local model from a concrete workload and acceptance test rather than a leaderboard or parameter count alone.
Do not start by asking, “What is the best local model?”
Start with the task.
A model that summarizes short private notes needs different strengths from one that reads screenshots, writes code, or calls tools across a long workflow.
Write one sentence describing the input and output:
Given one daily activity record, return one factual sentence under 25 words.Now collect representative examples. Include normal cases, empty input, unusual wording, long input, and content the model must not invent.
Define what good means. For the sentence above, we can check factual consistency, length, tone, latency, and whether the model adds unsupported details.
Only then compare models. Start with the smallest model that plausibly supports the task. A smaller model is easier to fit, faster to load, and cheaper to operate.
A leaderboard can help you create a shortlist. Your own examples decide which model belongs in the application.
Lesson completed