Skip to content
⌕Go Pro
☰

Learn

CoursesCareer pathsAll lessonsGlossary

Tools

CalculatorsCan I run it?PlaygroundBenchmarksFixes
Pricing

Extremely slow generation on a Mac

Symptom

Tokens trickle out, the machine lags, Activity Monitor shows heavy swap or red memory pressure.

Likely causes

  • Model + context exceeds the GPU-usable share of unified memory
  • Other apps consume RAM
  • Low Power Mode or thermal throttling

How to fix it

  1. Check memory pressure in Activity Monitor; close browsers and other heavy apps.
  2. Pick a smaller model/quant or shorter context; leave several GB free for macOS.
  3. Optionally raise the GPU wired limit (resets on reboot).
  4. Disable Low Power Mode and keep the machine plugged in.
bash
# example for a 64 GB Mac (value in MB), resets on reboot
sudo sysctl iogpu.wired_limit_mb=57344

Still stuck? Check the lessons or measure first with the benchmark lab.