Swiftlet
by leonickson1 (personal account)
Swiftlet is a Swift and Metal runtime that runs large Qwen Mixture-of-Experts models locally on Apple devices by streaming expert weights from storage, enabling 35B and 80B models to run with low RAM, including on iPhone. (description from the project’s GitHub page)
Repository facts
- Stars
- 659
- Forks
- 48
- Open issues and pull requests
- 11
- Primary language
- Swift
- License
- Apache License 2.0 (Apache-2.0)
- Owner
- leonickson1 · Personal account
- Created
- Aug 3, 2026
- Last push
- Sep 27, 2026
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 8,244: Helldez/BigMoeOnEdge
Run MoE models bigger than your RAM. Frontier-size MoE on a 12 GB phone, lossless, on stock llama.cpp
631 starsC++Apache-2.0Last push Oct 18, 2026
Rank 6,051: peonist-ai/halogen-flash-server
The fastest way to run Qwen3.8-Flash-Next on Strix Halo (gfx1151)
1,018 starsShellOther licenseLast push Oct 18, 2026
Rank 4,419: nobodywho-ooo/nobodywho
NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.
1,582 starsRustEUPL-1.2Last push Oct 17, 2026
Rank 2,336: nicedreamzapp/claude-code-local
Run Claude Code 100% on-device with local AI on Apple Silicon. MLX-native Anthropic-API server. 6 fighters incl. Muse-Glimmer 30B (now multimodal — reads images, abliterated), Gem…
3,369 starsPythonMITLast push Oct 15, 2026
Rank 6,122: kennss/SiliconScope
Sudoless Apple Silicon system monitor (native SwiftUI GUI) with ANE / Media Engine / memory-bandwidth tracking
999 starsSwiftMITLast push Oct 16, 2026
Rank 1,169: drumih/turbo-fieldfare
Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook
6,943 starsSwiftApache-2.0Last push Oct 15, 2026