Free open-source Windows app for running private local LLM chats, documents, and more than 40 GGUF models offline, including CPU-only systems.

Features
- Fully offline model inference
- No conversation data collection
- Support for 40+ GGUF models
- No dedicated GPU required
- Private LocalDocs document Q&A
Use Cases
- Privacy-sensitive AI chat
- Offline document Q&A
- Local-model use on Windows
- Running smaller models on CPU devices
- Work without reliable internet access
FAQ
Free open-source Windows app for running private local LLM chats, documents, and more than 40 GGUF models offline, including CPU-only systems. Core capabilities include: Fully offline model inference, No conversation data collection, Support for 40+ GGUF models.
Common scenarios include: Privacy-sensitive AI chat, Offline document Q&A, Local-model use on Windows.