AIQBTutorialsOrdinary
I Cut Dedicated GPU Memory to 4GB, and a Local LLM Still Ran at 90% Speed
Summary
On a Surface Laptop Ultra (RTX Spark, unified memory), I measured local LLM speed and Windows' free memory with the GPU's dedicated memory set to 4, 64, 82 and 96GB. Speed barely moved; memory left for Windows did.
CategoryAI Tutorials & Practice
TierOrdinary
Published
Indexed by AIQB
SourceDEV Community
AIQB record IDintel-02298bf0e300e871a414bca7