3 docs tagged with "model-selection"

Local coding-model candidates sorted by GPU memory and Apple Silicon unified memory, checked against official model cards on 2026-10-29.

Choose the model tier by task, count what caching and batch jobs save, check each provider's data defaults, and keep a short list of free APIs for prototypes.

A memory-first method for deciding which local model configuration fits and stays useful on one consumer GPU or an Apple Silicon Mac.