Skip to content
HearthworkHearthwork

Setup profiles

A profile captures a setup that works, together with the proof:

  • the model’s identity (file, size, fingerprint of the first 16 MB, quantization, architecture, chat template)
  • the runtime and llama.cpp build
  • installed agent versions
  • the effective server settings (context, KV type, slots, batch, fit target, any budget preset)
  • a hardware summary
  • the latest Doctor and benchmark results

Profiles live in profiles/ in the data folder.

Terminal window
hearthwork profile save [NAME] [--doctor]  # default name "default"; runs doctor --quick if no report from the last 24 h
hearthwork profile list | show NAME
hearthwork profile check [NAME] [--run]    # --run re-runs Doctor; a pass makes the profile verified again
hearthwork profile apply NAME              # model, context/slots/batch/KV and runtime build; Doctor validates afterwards
hearthwork profile apply previous          # the settings from before the last apply
hearthwork profile export NAME FILE        # no credentials, no device keys, paths replaced by placeholders
hearthwork profile import FILE             # stored as unverified; lists exactly what differs on this computer

Status

Section titled “Status”
StatusWhen
verifiedDoctor said “works” for every recorded agent.
needs recheckThe llama.cpp build, an agent version, the chat template or the model file changed. Run profile check --run.
unverifiedImported, or never checked.

hearthwork status shows profile: NAME (verified|needs recheck|unverified).

Safe to try

Section titled “Safe to try”

apply saves your current settings as the previous profile first, and restores them automatically if validation fails. Agent versions are only reported, never changed. See Doctor for what validation runs.