Solo researcher boosts Qwen 3.8 on Mac: +54% decode at 147k context

julianharris · x · 2026-08-29

Independent researcher Youssof released MTPLX V2.10, a full-stack performance overhaul for running Qwen 3.8 on Mac — praised by Julian Harris as a one-man local AI powerhouse, spanning low-level kernel optimizations inside the model plus a custom inference server. Highlights:

Harris suggests Jeremy Howard's Answer.ai should snap him up before Big Tech does.

Original post →

More from Infra

Infra channel →