Sharing a recording and notes from my demo at AI Tinkerers Seattle last week. I ran 6 different models in parallel on identical coding tasks and had a judge score each output on a 10-point scale.
Local models (obviously) didn't compare well with the cloud counterparts for this experiment. But I've found them to be useful for simpler tasks with a well defined scope e.g. testing, documentation, compliance. etc
Local models (obviously) didn't compare well with the cloud counterparts for this experiment. But I've found them to be useful for simpler tasks with a well defined scope e.g. testing, documentation, compliance. etc