15:59
2026-08-18
forum.level1techs.com
large-language-models
Is there a point messing with Strix Halo 395 64GB if I have a 5090?
A user asks whether a 64GB Strix Halo 395 machine is useful for local LLM inference alongside an RTX 5090, noting the main advantage is loading models larger than 32GB into memory despite slower infer…