I ran local LLMs on Intel's cheapest iGPU, and the results were surprisingly decent

XDA developers | May 31, 2026, 7:30 a.m. | Original
It ain't no match for a dedicated GPU, but you can run some light LLMs on the N100
Buying a GPU in 2026 means buying a software ecosystem, not a graphics card Immich finally feels good enough on my NAS that I deleted Google Photos for real this time