[maiconburn]

This looks really interesting.

Quick question, which models are you using with Ollama for analysis? I’ve been testing a few locally, and hardware requirements vary a lot, so not everyone can run the heavier ones.

Have you done any benchmarking or have a recommended model for this use case?

[Wewoc]

AnythingLLM + qwen2.5:14b is what I use — good for pattern recognition across metrics you wouldn't think to look for manually.

For everything else the HTML dashboards honestly do a better job. garmin_analysis.html shows your daily values, personal 90-day baseline and age/fitness reference ranges all in one view. Most questions answer themselves just by looking at it.

[mresteves]

I'm interested to know as well.