Joey(@aijoey):Qwen Image 2.1 Turbo on a 24 GB M4 Mac, no app needed 👀 Two MLX quants that run with plain mflux and the correct 8-step Turbo schedule: - 4-bit: 52s, 4.71 GB peak - 6-bit: 54s, 6.34 GB peak (0.999 match to official BF16) - zero swap at 512x512 6-bit at 1024x1024: 3m 40s, 8.45 GB peak https://t.co/veUataU7xp If you run it, drop your Mac and your times below.

Joey

@aijoey

Testing local AI models on real tasks. Reviews, tools & practical workflows. Dev Ambassador @antlingagi @Alibaba_Qwen @openbmb

가입 July 2017

1.5K 팔로잉 중 4.9K 팬

Joey@aijoey

2026.10.10 04:28

Qwen Image 2.1 Turbo on a 24 GB M4 Mac, no app needed 👀 Two MLX quants that run with plain mflux and the correct 8-step Turbo schedule: - 4-bit: 52s, 4.71 GB peak - 6-bit: 54s, 6.34 GB peak (0.999 match to official BF16) - zero swap at 512x512 6-bit at 1024x1024: 3m 40s, 8.45 GB peak If you run it, drop your Mac and your times below.