# An Open-Source Runtime Streams Mixture-of-Experts Weights From SSD to Run an 80-Billion-Parameter Qwen on a Mac

Swiftlet keeps only the dense core in memory and fetches each routed expert with a single disk read, putting a 35-billion-parameter model on an iPhone at roughly one token per second.

- Published: 2026-08-04T06:16:46.804Z
- Canonical: https://polylog.news/ai/2026-08-04/an-open-source-runtime-streams-mixture-of-experts-weights-fr
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Swiftlet (GitHub, via Hacker News)](https://github.com/leonickson1/Swiftlet)

A Swift and Metal runtime called Swiftlet applies a straightforward observation about sparse models to deployment. In a mixture-of-experts (MoE) model, only a small fraction of parameters activate per token, so the routed experts do not nee…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-08-04/an-open-source-runtime-streams-mixture-of-experts-weights-fr (subscription information: https://polylog.news/pricing).