# StayLameBro/backburner

> A llama.cpp fork that plugs an iPhone into a Mac over USB-C and splits the work: the Mac runs layers 1-40, the iPhone runs 41-64 on its GPU, speeding up prefill and allowing context up to 196k-229k tokens. Aimed at people running Qwen3-27B locally on a memory-constrained Mac.

- Magnitude: 5.2 out of 10 — Early signal
- Stars: 91 total · +0 stars today, ≈ 77 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Objective-C++ · License: MIT · Created: 2026-10-01 · Last push: 2026-10-03
- GitHub: https://github.com/StayLameBro/backburner · Page: https://gitnova.dev/en/r/StayLameBro/backburner

## Useful for

- Speed up reading long files and tool results in a local agent on a Mac
- Extend session context to 128k+ tokens on a 24 GB MacBook
- Run Qwen3-27B locally using the iPhone GPU for part of the layers

## Why it’s here

- 0 stars so far today, about 77 expected by the end of the day.
- The spike has held for 2 days in a row — not a one-off blip.
- The repository is 2 days old and already has 91 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #112.
- About 24 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 6
- Issues and pull requests: 0
- Watchers: 1
- Average over the last week: 56 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 9
- Latest release: v0.0.1 (2026-10-03)

## Stars per day, last 7 days (oldest → newest, today is partial)

2026-09-27 … 2026-10-03: 0, 0, 0, 0, 0, 91, 0

## Magnitude by day, last 2 days

10-02 4.5, 10-03 5.2

## Spotted in now

- Top new repositories this week: #112

## More in this category

1. **Niko1221/Strata** — 8.0 · Breakout · Language models · C++ · +0 stars today, ≈ 1,200 by evening
   A C++ local inference engine that runs the 125B MoE model Qwen3.8-Flash-Next on a regular PC with one NVIDIA GPU (12-24 GB) and 64 GB RAM, exposing an OpenAI/Anthropic-compatible API on localhost.
   Full card: https://gitnova.dev/en/r/Niko1221/Strata.md
2. **Kutuyyy/Leaked-System-Prompt-AI** — 5.1 · Early signal · Language models · +0 stars today, ≈ 63 by evening
   A repository that collects and documents system prompts, instructions, and tool definitions of major AI models and agent platforms (OpenAI, Anthropic, Google, Cursor, Devin, etc.) for studying their behavior.
   Full card: https://gitnova.dev/en/r/Kutuyyy/Leaked-System-Prompt-AI.md
3. **Vibra-Ingenn/Janus** — 5.0 · Early signal · Language models · Go · +0 stars today, ≈ 34 by evening
   Local LLM server in Go: runs .gguf models via llama.cpp (Vulkan or CPU) and exposes an OpenAI-compatible API with a web UI and built-in tools.
   Full card: https://gitnova.dev/en/r/Vibra-Ingenn/Janus.md
4. **ninjahawk/livenerf** — 4.3 · Early signal · Language models · Python · +0 stars today, ≈ 74 by evening
   A benchmark for tracking whether a frontier model quietly degrades after release: it runs a frozen question panel daily and statistically measures drift in accuracy and token counts against the launch-week baseline.
   Full card: https://gitnova.dev/en/r/ninjahawk/livenerf.md
5. **firelex/jeff** — 4.1 · Cooling · Language models · Python · +0 stars today, ≈ 34 by evening
   Small fine-tuned Qwen3.5 and Gemma 4 models for zero-shot classification: given a situation description and a list of options, they return a calibrated probability for each option in a single forward pass.
   Full card: https://gitnova.dev/en/r/firelex/jeff.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-03 01:56 UTC, updated every 30 minutes.