Obsidian is already great, but my local LLM makes it better ...

Use the vitals package with ellmer to evaluate and compare the accuracy of LLMs, including writing evals to test local models.

The new lineup includes 30-billion and 105-billion parameter models; a text-to-speech model; a speech-to-text model; and a vision model to parse documents.

In practice, the choice between small modular models and guardrail LLMs quickly becomes an operating model decision.