StayLameBro/backburner: Your iPhone helps your Mac run a 27B model: faster prompt reading and more context over a USB-C cable
Your iPhone helps your Mac run a 27B model: faster prompt reading and more context over a USB-C cable Language: Python.
ProofCode ↗
Key points
- Topics: apple-silicon, ios, iphone, llama-cpp, llm-inference, local-llm, macos, metal, qwen, sme2, speculative-decoding.
Sources (1)
- [1]StayLameBro/backburner: Your iPhone helps your Mac run a 27B model: faster prompt reading and more context over a USB-C cableRising AI repositories on GitHub · Oct 1, 08:59 PM
Your iPhone helps your Mac run a 27B model: faster prompt reading and more context over a USB-C cable Language: Python.
Topics: apple-silicon, ios, iphone, llama-cpp, llm-inference, local-llm, macos, metal, qwen, sme2, speculative-decoding.
Extractive summary: sentences quoted from the sources.
Before this
- Sep 30, 2026axolotl-ai-cloud/axolotl v0.20.0
- Sep 22, 2026vllm-project/vllm v0.30.0
- Sep 15, 2026ollama/ollama v0.34.2
- Sep 9, 2026vllm-project/vllm v0.29.0
- Aug 26, 2026vllm-project/vllm v0.28.0
- Jun 9, 2026Introducing Gemma 4 12B: a unified, encoder-free multimodal model