My RTX 5090 can't keep up with Apple Silicon on the biggest local LLMs, and I hate to admit it

XDA developers | May 14, 2026, 7 a.m. | Original
They don't win on speed, but they do win on being able to run them in the first place.
NotebookLM is great until your sources outgrow it, and that came faster than I expected I ditched ChatGPT Plus, and Gemini's free tier handled my entire workflow surprisingly well