Find tools › Open-source projects › Keep data private

backburner

Open-source project · by StayLameBro

Use your iPhone as a co-processor to make local AI run faster and hold larger documents on your Mac.

Some setupWell known

What it costs

Free and open source; you may pay for the AI model it uses.

Use it to

  • Run large local models with extended context windows
  • Speed up file reading for coding agents
  • Offload model memory onto an iPhone

How to start

  1. Connect your iPhone to your MacBook using a 10 Gb/s USB-C cable.

  2. Install the accompanying Backburner iOS app on your phone.

  3. Launch the local server script to start sharing the model workload.

Good to know. This is a low-level experimental project relying on a custom llama.cpp fork and requires connecting devices over high-speed USB-C.

Before you install

  • Found automaticallyNot reviewed by a person yet. Check it before installing.
  • License: MITYou are allowed to use it under these terms.
  • Last updated 2026-11-07

More detail

Plug an iPhone into a Mac over USB-C to share the workload of running a local 27B AI model.

Local AI models on a Mac are constrained by memory and speed when processing long prompts. This bridges an iPhone's GPU and memory to speed up reading files and handle much larger contexts without buying a bigger computer.

Similar tools

Descriptions are written in plain English from each project's own documentation and refreshed by our agent; this one was last checked 2026-10-03. Spotted a mistake? · Open in Find tools · © 2026 Which AI Map