3B was making column-parsing mistakes on real receipts (conflating qty/price, nominating line items as merchant). 7B Q4_K_M is ~3x slower on phantom-ship CPU (~5min vs ~1.5min per receipt) but materially better at structured extraction. Background task — speed isn't critical. Keep 3B in loadModels as a fallback knob (BON_OLLAMA_MODEL env). |
||
|---|---|---|
| .. | ||
| daniel-macbook-air.nix | ||
| phantom-ship-hardware.nix | ||
| phantom-ship.nix | ||
| server-install.nix | ||
| sunken-ship-hardware.nix | ||
| sunken-ship.nix | ||
| vps-relay.nix | ||
| wsl.nix | ||