cercano-models

To list available models on your local Ollama instance, you can use a discovery skill that queries the connected backend. It enumerates all installed models, returning their names, sizes, and last modified dates for easy selection.

When discovering local models for inference, you receive the model names, file sizes, and last modified dates. This pre-qualification data helps you compare and pick appropriate models before running inference or switching active deployments.

Yes, discovering Ollama models requires a Cercano server running and actively connected to your Ollama instance. This backend connection is necessary to enumerate the installed local models and retrieve their metadata.

The best way to compare local models before switching active inference backends is to enumerate them by size and recency. Reviewing the last modified dates and file sizes helps you decide which model to deploy for a specific development task.

Yes, you can use this skill to check model sizes for production tasks. It enumerates all models on the active Ollama backend, providing the size and recency data needed to pre-qualify and optimize your local inference setup.