I Cut Dedicated GPU Memory to 4GB, and a Local LLM Still Ran at 90% Speed
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. This is an English adaptation of an article I originally published in Japanese on Ze…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-11-15 10:22 · DEV Community — AI
I Cut Dedicated GPU Memory to 4GB, and a Local LLM Still Ran at 90% Speed