GECO AI
Local inference uses your own compatible hardware to run a model.
The model calculation happens on your device. This can give you more control over execution, but does not prove that every part of the platform is offline. Account information, messaging and metadata may still use GECO services.
Check memory, storage, model license and supported runtime before installation. Keep the computer connected when you expect to use its models remotely. Electricity, storage and hardware still have costs even when inference is local.