Show HN: Run an 80B Qwen in 4.3 GB of RAM on a Mac, and a 35B on an iPhone
2.70T2 sourceHacker News · Show HN (50+ points)
Source record
Published by Hacker News · Show HN (50+ points) (T2 source). The original is at https://github.com/leonickson1/Swiftlet.
Pipeline notes
The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.
SummaryShow HN for Swiftlet, an open-source project that runs an 80B Qwen model in 4.3 GB of RAM on macOS and a 35B model on an iPhone, using aggressive quantization. GitHub repo linked, 50+ points on Hacker News.
Why it mattersConcrete open-source tool pushing the floor on memory needed for local LLM inference on Apple silicon. Useful for readers exploring on-device AI setups without cloud APIs.

Cited by
No citations on record.
