Resident model
swapping requires step-up โ assert a passkey first. The old model is unloaded before the new one is loaded (one model fits the iGPU at a time), so turns during the load are refused and fall back to the classifier.
a swap is not remembered. Nothing writes it down, so the next restart of the daemon โ including the one mavupdate does โ comes back on phraser.model_path from the config. Make it stick by editing that.
swap not configured
this core has no phraser.swap_models allowlist, so there is nothing to swap to. Add the gguf paths you allow to deploy/mavend.json and restart once.