PRODUCTIVITYDays to result82% confidence

Right-Sized AI Selection

Match model size to task complexity and measure energy cost before defaulting to the biggest available LLM.

Problem it solves

Defaulting to the biggest available LLM for every query, which inflates cost and energy footprint without proportional quality gains.

Best for

Builders, teams, and individual users choosing which AI model to deploy or query for a specific task.

Not ideal for

Frontier research that genuinely requires the broadest capability surface or unknown-task exploration.

Overview

Why this framework exists

Right-Sized AI Selection rejects the bigger-is-better default and treats model choice as an engineering decision with cost, energy, and accuracy tradeoffs. The premise: most AI queries are narrow tasks (a fact lookup, a classification, a summary) and a small, task-specific model handles them with comparable quality at a fraction of the energy and dollar cost.

The framework begins with task scoping. Before reaching for a general-purpose LLM, define what the model actually needs to do. Luccioni's research found general LLMs use up to 30x more energy than task-specific models for simple questions, and a small model can answer with 1/150th the energy of a large reasoning model on equivalent prompts.

Next comes capability matching. Map the task to the smallest viable model class: a 135M-parameter small LM for short factual queries, a domain-tuned model for vertical work (weather, bioacoustics, satellite imagery), and a frontier LLM only when generality is genuinely required. Run small models locally on phone or browser when privacy and latency matter.

Finally, instrument and disclose. Track energy or cost per call, prefer providers that publish efficiency scores, and build the habit of treating compute like any other consumable input rather than a free resource.

Core principles

5 total
  1. Bigger is not better by default; model size should be justified by task complexity, not assumed.
  2. Task-specific models routinely match or beat general LLMs on narrow workloads while using a fraction of the energy.
  3. Every AI call has a measurable energy and carbon cost, and that cost should be visible to the person making the choice.
  4. Local execution on small models delivers privacy, sovereignty, and latency benefits that cloud LLMs cannot match.
  5. Diversity of model approaches (vision, time-series, acoustic, physics-based) often outperforms a single LLM forced into every domain.

Checklist

Saved in your browser

Origin story

How this framework came to be

Developed by Sasha Luccioni, AI researcher at Hugging Face, who led the AI Energy Score project benchmarking 100+ open-source models and published peer-reviewed studies comparing energy use across LLM and task-specific architectures.

Source

Traced to primary
Source · PODCAST
We're Doing AI All Wrong. Here's How to Get It Right
Sasha Luccioni
Open source →

Related frameworks

Browse all Productivity →