Running 104GB Qwen Model on 48GB Mac via SSD Streaming

carloslfu · hn · 2026-09-02

The author presents slotstream, a method to run the 125B parameter Qwen3.8-Flash-Next 4-bit model on Macs with as little as 16GB RAM—normally requiring 100GB+ memory. It leverages expert-offloading and SSD streaming. Built with Apple's MLX and Swift, it features an auto-mode for balancing memory and speed, with speculative decoding support planned.

Original post →

More from Infra

Infra channel →