TutorialsOrdinary
We tested every small model our camera agent uses on a 4-core CPU. The bigger model lost.
Summary
Tool calling, vision, speech to text, text to speech and search, measured on 4 vCPUs with no GPU. The harnesses are open so you can rerun them.
CategoryAI Tutorials & Practice
TierOrdinary
Published
Indexed by AIQB
SourceDEV Community
AIQB record IDintel-105124e264e9ff9f02503919