devtool
Show HN: Run an 80B Qwen in 4.3 GB of RAM on a Mac, and a 35B on an iPhone
Impressive low‑RAM local LLM inference, but limited ecosystem and uncertain long‑term support.
5.5Overall
Utility6
Onboarding5
Craft5
Niche fit6
Longevity5
Five dimensions scored independently; overall is a weighted average. Scores are only comparable within this same rubric.
Good for
Developers who need to run Qwen models locally on macOS or iOS
Not for
Teams without a specific Qwen requirement or that need enterprise‑grade support
Project description
github.com
Alternatives
llama.cppggmlmlc-llm