Back to News
Models
Show HN: Run an 80B Qwen in 4.3 GB of RAM on a Mac, and a 35B on an iPhone
Github.com·August 3, 2026·1 min read
AI Summary
A new project allows users to run an 80 billion parameter Qwen model on a Mac with only 4.3 GB of RAM and a 35 billion parameter model on an iPhone. Developers can contribute to the Swiftlet project by creating an account on GitHub.
From the source
Contribute to leonickson1/Swiftlet development by creating an account on GitHub.
The full text couldn't be loaded here (the source may require a subscription).
View original at Github.comKeep reading
Tokenomics: Why making AI pay is trickyBBC News · 1d ago[Sponsor] MCP vs. REST: The Right Way to Connect Agents to Your APIWorkos.com · 1d agoPalantir's Karp renews attacks on frontier AI labs that are 'trying to drug addict us'CNBC · 1d agoThe AI Act kicks into action, forces companies to be clear about AI botsMalwarebytes.com · 1d ago
Was this useful?