ggml-org/Llama-Windows
Windows system tray app for local LLMs
- Chart
- Not on a chart right now
- Stars
- 468
What it is
Llama is a Windows 11 WinUI 3 tray app for running llama.cpp models locally. It manages a local llama serve process via its REST API and stores models in the standard Hugging Face cache.
Who it is for
Windows users and developers who want to run local LLMs with minimal setup from the system tray.
Why it is trending
The repository gained 240 stars today out of 465 total stars, following its v0.14.1 release. It stands out with zero-telemetry local execution and an Alt+Space overlay that hides instead of closing to keep conversations intact.
Main features
- Borderless, Mica-backed flyout anchored to the Windows system tray
- Uses an existing llama.exe or downloads one automatically
- Context-length picker with per-option memory estimates read from GGUF headers
- Alt+Space overlay to summon the model WebUI from any app
Summarized on November 18, 2026 from the README and repository data. It can be wrong; check the source before relying on it. Report a wrong summary