No. 5 of 14 · Diamonds in the rough · 7 October 2026
An iPhone that helps a Mac run a 27B model
Plug an iPhone into a Mac with a 10 Gb/s USB-C cable and, its README says, the phone runs the last 24 layers of Qwen3.8-27B, so the Mac reads prompts faster and holds more context. The README says it was tested on an M4 Pro MacBook Pro with an iPhone 17 Pro Max and a 16 Pro Max, on the author’s own fork of llama.cpp.
Score 5 of 9: new 3 of 3, momentum 0 of 3, evidence 2 of 3. Momentum measured: 825 to 825 stars in 0.04 hours (0.0% a day), read 2026-10-07T14:36:32Z. Two minutes apart, too close to show movement; re-check due 9 to 10 October.
- Who started it
- github.com/StayLameBro, 1 October. The first X post, a day later, is from @StayLameBro1; the GitHub profile does not name that account, so the match is ours, from the post’s details
- How we found it
- GitHub search first; then X, where another account linked it, and Hacker News
Why it matters Local agents spend much of their time reading files and tool output. If the numbers hold, a phone people already own cuts that wait.
The receipt
5 facts: 3 SAW, 2 STATED. SAW: fetched and read by us. STATED: a source’s own claim, quoted. Check any line against its source before you repeat it.
- STATED 29 to 44 percent faster prompt reading at 16k to 48k tokens of context, and 196k to 229k tokens of 8-bit context with an iPhone 17 Pro Max, where the Mac alone fits 64k Stated by backburner README.
- STATED “Same answers. Greedy output is token-identical with and without the phone” Stated by backburner README.
- SAW Repo created 1 Oct 2026 at 20:59 UTC: 825 stars, 81 forks Read 7 Oct 2026 14:36 UTC.
- SAW First X post we found, @StayLameBro1, 2 Oct 2026 at 15:35 UTC: 56,255 views from an account with 334 followers Read 7 Oct 2026 14:45 UTC.
- SAW Linked on X by another account, @needmorevram, 2 Oct 2026 at 22:57 UTC
Sources
- github.com/StayLameBro/backburner
- x.com/StayLameBro1/status/2106045335290228959
- x.com/needmorevram/status/2106156718740943182
Where it was published
First published on in the Edition of 7 October 2026, which is kept as it was published: its stories, facts and scores never change. See it in the 3D map, where your agent can take you to it.
For agents: this story’s id is 2026-10-07/backburner. Through our agent door, get_story gives it with every receipt;
llms.txt says how. Seen something we missed? Send a tip or a correction.
More from the edition of 7 October 2026
- Gemini 4 Argon: 9.6 million views in a week
- Karpathy’s ladder for reading what models write
- Twelve hours of Claude, six million views
- Mistral Large 4: an API now, open weights promised for late October
- Video for coding agents, rendered straight on the GPU
- Karpathy’s tips became an agent skill within ten hours
- A motion design studio where you approve every stage
- An index that lets agents search big datasets cheaply
- A skill that holds AI motion graphics to a designer’s standard
- A push to talk device for an agent you run yourself
- Motion design that keeps Persian letters joined
- Your coding agent’s sessions, on your own server
- A Mac video editor your coding agent can drive