Cost
Open-source runtime under Apache-2.0. Check the chosen model's separate license.
Read pricing sourceReviewed
Swiftlet
Run large language models like Qwen locally on Macs and iPhones with high efficiency.
Why it made the shelf
Swiftlet is an open-source tool for running LLMs locally on Apple hardware, which fits the developer and AI tool.
On 5 boards
- First seen
- 2 months ago
- Best score
- 310 points · 140 comments
From official documentation
Product details
What it does
Use streamed local Qwen models through a Swift library, command line, or local OpenAI-compatible chat server.
Read the sourceReviewed
Know before you choose
Targets Apple devices on macOS 14 or iOS 17 and later. Model containers need substantial storage: the documented 4-bit 35B model uses 18 GB.
Read the sourceReviewed
Official signals
What the source shows.
Sourced facts from the places where this tool ships.
From GitHub
- GitHub stars
- 580
- Last code update
- 2026-09-03
Behind the tool
Who built it. How it grew.
People, backing, growth, and ownership. Every claim links to its source.
Official sitegithub.com
Source review current
Public trail
Where it showed up
6 references from 4 publishers.
- First trace
- Hacker News2 months ago
- Strongest thread
- Hacker News140 comments
- 01Hacker NewsFirst traceStrongest discussion
Run an 80B Qwen in 4.3 GB of RAM on a Mac, and a 35B on an iPhone
