[All work](https://boiko.ai/work/)

Model evaluation · Cost-aware routing

# local-enough

Compare local and cloud options for a task, then route requests to the least expensive option that clears its quality bar.

[Explore the repository](https://github.com/B0yko/local-enough)

---

## [Quality before cost.](https://boiko.ai/work/local-enough/#quality-before-cost)

Running a smaller model locally is useful only if it can do the job well enough. local-enough evaluates local models, cloud models, and non-LLM baselines on five back-office tasks: CRM extraction, intent classification, PII redaction, meeting summarization, and vendor matching.

The benchmark records task quality, output validity, latency, throughput, per-task cost, and an estimate of hardware and energy costs. It selects routes on a calibration split and reports held-out test results separately.

## [Turn measurements into a route.](https://boiko.ai/work/local-enough/#turn-measurements-into-a-route)

A generated plan connects the evaluation to an OpenAI-compatible router. Deterministic checks reject malformed results, and requests can fall back when a selected route fails. A local-only setting refuses cloud escalation; if no local candidate meets the quality bar, the router returns an error by default instead of quietly lowering the standard.

## [A useful “no” is a result.](https://boiko.ai/work/local-enough/#a-useful-no-is-a-result)

In the published reference run, a local option cleared the quality bar for two of five tasks: intent classification through a TF-IDF baseline and vendor matching through a small local model. The best local PII-redaction result reached 92.2% against a 95% bar, so the local-only route declined that task.

The reference workload suggested a lower-cost mixed route, but no single cloud model met every task bar. The cost comparison is a scenario estimate, not a measured production saving.

[Reference results](https://github.com/B0yko/local-enough/blob/37ef7fbaa30d90496a9f5178cf6ae09d75f67fd1/README.md#results)

## [Where the evidence stops.](https://boiko.ai/work/local-enough/#where-the-evidence-stops)

Four of the five datasets use templates, and the reference local runs used one Apple Silicon machine, English inputs, a dated price snapshot, and configured rather than measured power consumption. The router is a reference implementation and has no built-in authentication. Each new workload needs its own quality bar and evaluation.

[Study limitations](https://github.com/B0yko/local-enough/blob/37ef7fbaa30d90496a9f5178cf6ae09d75f67fd1/README.md#limitations)

Source: [https://boiko.ai/work/local-enough/](https://boiko.ai/work/local-enough/)