sebytzr16/on-device-llm
Private, offline AI assistant for Android and Windows: run local LLMs (Gemma 4, Qwen, any GGUF) on your phone or PC with llama.cpp, CUDA and Vulkan. Parallel local AI agents, voice, documents, photos, cited web research. No account, no cloud.
GitHub repository with 12 stars and 2 forks.
Language: Dart
Topics: ai-agents, ai-assistant, android, chatgpt-alternative, cuda, flutter, gemma, gguf, llama-cpp, llm