backburner
Your iPhone helps your Mac run a 27B model: faster prompt reading and more context over a USB-C cable
The Lens
By Erik Loyd, SaaS CEO and former COO/CFO of an AWS Premier Partner.
Updated Oct 2026
Backburner turns your iPhone into a helper GPU for your Mac. Plug a recent Pro iPhone into an Apple Silicon Mac over a 10 Gb/s USB-C cable and it helps run Qwen3.8-27B locally: the phone runs the last 24 layers while the Mac reads your prompt, 29-44% faster at 16k-48k of context in the maintainer's tests. It also holds the oldest context past 64k. Free, MIT.
Setup is real work: a 24 GB Apple Silicon Mac, an iPhone 15 Pro or newer, Xcode, and the app sideloaded through AltStore with a free Apple ID that re-signs every 7 days. One curl | bash pulls about 24 GB of models, then backburner serves an OpenAI-compatible API on localhost. Its llama.cpp fork alone more than doubles writing speed over stock.
Solo developers running local coding agents: free, worth an afternoon. Teams: skip it, it handles one request at a time on one desk.
The catch: it's pre-release, and the phone must stay unlocked with the app in front. Past 64k, a locked screen stops the server. Below 64k the phone doesn't speed up writing at all. Versions before 0.0.3 answered anyone on Wi-Fi with no auth, so update.
Free vs Self-Hosted vs Paid
fully freeFree: Everything. The code is MIT, the bundled llama.cpp fork keeps llama.cpp's MIT license, and the default model (Qwen3.8-27B, IQ4_XS GGUF, 15.5 GB) and the DFlash2 draft model are Apache-2.0 on Hugging Face. There is no paid tier, account or cloud service.
Self-hosted: It only runs on your own hardware: an Apple Silicon Mac on macOS 14+ (the installer requires 24 GB unless you set FORCE=1; users report 8 GB and 18 GB Macs working with the smaller IQ2_XS model), an iPhone 15 Pro or newer or an M-series iPad, and a 10 Gb/s USB-C cable. The app installs through AltStore with a free Apple ID (re-signed every 7 days, 3 sideloaded apps per free account) or builds with Xcode. A fresh install downloads about 24 GB, and sudo sysctl iogpu.wired_limit_mb has to be re-run after every reboot (the backburner command does it for you).
Paid: No paid tier. The hidden costs are hardware: the phone, a Mac with enough memory, and a 10 Gb/s USB-C cable, because the one in the iPhone box is USB 2 and too slow. A paid Apple developer team only stretches app signing from 7 days to a year.
Free and MIT licensed; the only spend is a 10 Gb/s USB-C cable if you don't own one. It pays off only if you already run a 27B model on a 24 GB Apple Silicon Mac and have an iPhone 15 Pro or newer on the desk.
What to do by team size
- Solo
- free; worth trying if you already run a local 27B model on a 24 GB Apple Silicon Mac and own an iPhone 15 Pro or newer
- Small team
- free, but it is a per-developer desk setup serving one request at a time, not a shared server
- Medium team
- not a fit; run a shared inference server on real GPUs instead
- Large team
- not a fit
Get tools like this every Wednesday
One featured tool, three on the radar. No fluff.
A low score is not a verdict on quality. Young and niche tools start low by design. How we calculate scores
Trust Signals
License: MIT License
Use freely, including commercial. Just keep the license.
Commercial use: ✓ Yes
About
- Owner
- StayLameBro (User)
- Stars
- 1,101
- Forks
- 109