Desktop appPersonal and daily life
Oxide-Lab
Load local language models for private, offline desktop chat.
- Stars
- 115
- Forks
- 6
- Updated
- Updated Jul 6, 2026
Apache-2.0
Load local language models for private, offline desktop chat.
Oxide Lab provides a desktop chat interface that runs compatible language models entirely on the user's machine. It loads GGUF or SafeTensors models across several Llama, Qwen, Mistral, DeepSeek, and related architectures, with CPU, NVIDIA CUDA, or Apple Metal acceleration. Users must obtain a compatible model before chatting, and larger models require more memory than the stated 4 GB minimum.
Resource types
Use cases
Runtime
Control external display brightness and volume with Mac keys or menu sliders.
Set videos, webpages, or apps as animated Windows wallpapers
Capabilities
Public GitHub facts last synced Jul 14, 2026.
Manage Epic, GOG, and Amazon games across Linux, Windows, and macOS.
Schedule short and long break reminders while working at a computer.