---
title: "slotstream"
description: "Streams MoE experts from SSD so a 125B 4-bit Qwen can run on Macs with far less RAM, via MLX/Swift with an Ollama-compatible API."
canonical: "https://vibing.inc/library/slotstream-vg-2159"
category: "Dev Utilities & Vibe-Coding Tooling"
subcategory: "Local-first & sync"
license: "MIT"
author: "Carlos Galarza (@carloslfu)"
source: "https://github.com/carloslfu/slotstream"
---

# slotstream
Streams MoE experts from SSD so a 125B 4-bit Qwen can run on Macs with far less RAM, via MLX/Swift with an Ollama-compatible API.
## Facts
- Source: https://github.com/carloslfu/slotstream
- Category: Dev Utilities & Vibe-Coding Tooling / Local-first & sync
- Author: Carlos Galarza (@carloslfu)
- Licence: MIT
- Tags: mlx, local-llm, macos, moe, ollama
## Why it's a gem
Makes huge local models practical on ordinary Mac memory budgets.
---
Listed in The Vibeary: https://vibing.inc/library/slotstream-vg-2159 · JSON: https://vibing.inc/api/public/library/gems/slotstream-vg-2159