The outcome

Choose an open model based on evidence for the intended task and operating environment.

Step by step

A workflow you can repeat.

  1. 01

    Define the task, languages, modalities, hardware, latency, context, safety, and license requirements.

  2. 02

    Filter Hub results and inspect model cards, files, license, training disclosures, limitations, and recent activity.

  3. 03

    Test candidates in widgets or the Inference Playground using the same representative and adversarial examples.

  4. 04

    Record output quality, provider, configuration, latency, cost, and failures, then reproduce the test in code.

  5. 05

    Pin the model revision and document evaluation results, license obligations, and monitoring before integration.

Working standard

What good use looks like.

  • Read the full model card.
  • Pin revisions for reproducibility.
  • Evaluate your task, not a leaderboard alone.

Official references

Check the current product documentation.