Llama Windows
#3 in Lokale LLM-RuntimesLlama Windows · 2× · tolest 01. Nov. 2026
49
Momentum
Llama Windows is a free, open-source desktop app for Windows 11 (x64 and ARM64) that runs llama.cpp from the system tray. Models can be downloaded in one click from the Hugging Face Hub, and the app provides a local, OpenAI-compatible server. It is the Windows counterpart to llama.app for macOS.
Momentum-Verloop
03.08.01.11.
Features
| License | MIT (per repo) |
| Platform | Windows 11 (x64, ARM64; native on Windows on Arm and NVIDIA RTX Spark) |
| Price | Free |
| Protocol Compatibility | OpenAI-compatible API at http://localhost:9931/v1 |
| Supported Models/Providers | Models from the Hugging Face Hub (GGUF format), recommended models in panel |