Qwen-Image local on a 24GB MacBook Pro takes 5-6 minutes per image

vista8 · x · 2026-09-22

A user ran Qwen-Image 2.1 locally (with a safety-checker-removed decoder) on a 24GB MacBook Pro and got 5-6 minutes per image. Verdict: without a proper GPU, local models — text or image — are a waste of time and disk space. A useful real-world data point for anyone considering on-device image generation.

Original post →

More from Infra

Infra channel →