Perhaps I was too premature in declaring maxed out modern hardware as the only option for local AI.
Got about 6.2x my LM Studio generation speed testing out TensorFold with DFlash2 and disk caching on my M1 Max.
Time to first token (TTFT) on a cached prompt dropped from 152s
If you can't afford the latest, most expensive hardware, local AI is all about trade-offs. And some trade-offs are more dangerous than others.
— Ðaniel ₩onder (@danielwonder) October 31, 2026
Using the best model generally recommended for my era of hardware (Qwen3.8 27B 8-bit on a 64GB M1 Max, Hermes Agent, 64K context,… pic.twitter.com/xMjS7zR0Vl