StayLameBro/backburner
Your iPhone helps your Mac run a 27B model: faster prompt reading and more context over a USB-C cable
Older snapshot: check the original source for current information.
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
Plug your iPhone into your MacBook with a 10 Gb/s USB-C cable and it helps run Qwen3.8-27B locally: on its GPU, pipelined. Your agent waits less every time it reads a file or a tool result of more than 512 tokens: 29-44% faster prefill at 16k-48k. and computes attention over it: its GPU during prefill, its GPU and Neural Engine while writing. The server sizes the total from the phone's free memory at startup (196k-229k tokens at 8-bit on an iPhone 17 Pro Max). Tested end to end to 128k at 8-bit and 140k at 4-bit. The engine is a llama.cpp fork (llama.cpp/, StayLameBro/backburner-llama.cpp) with its own Mac kernels (SME2, Metal fusions, DFlash2 speculative decoding). Those speed things up on the Mac alone too; the numbers below keep the two apart. Tested on a MacBook Pro M4 Pro (24 GB) with iPhone 17 Pro Max (A19 Pro) and iPhone 16…
Read the full README ↗ · Preview checked 2026-11-11T21:17:53.297Z
Inside the original README — Document outline
- Backburner
- Results
- Reading (prefill): Mac alone vs Mac + iPhone, same build
- Writing (decode)
- Context you can hold
- Will it work on my …?
- How it works
- Who does what
- The pieces
- Limits
- Security
- Setup
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: MIT. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
Your iPhone helps your Mac run a 27B model: faster prompt reading and more context over a USB-C cable
Repository facts
- Owner
- StayLameBro
- Primary language
- Python
- Stars
- 874
- Forks
- 85
- Open issues + pull requests
- 6
- License
- MIT
- Archived
- No
- Default branch
- main
- Created
- 2026-10-01T20:59:56.000Z
- Last push
- 2026-10-06T01:43:05.000Z
Topics and intended use
Owner-supplied topics: apple-silicon, ios, iphone, llama-cpp, llm-inference, local-llm, macos, metal, qwen, sme2, speculative-decoding
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-10-08T12:06:17.489Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related repositories
EbookFoundation/free-programming-books
donnemartin/system-design-primer