llama-cpp 3 One Small Model, Many Skills: Switching LoRA Adapters On-Device to Get the Most Out of a Mobile SLM Jul 1, 2026 How to Run a 1-Bit LLM On-Device with llama.cpp: Deploying Bonsai on iOS Jun 29, 2026 Skills You Need to Become an Exceptional On-Device AI Engineer Jun 22, 2026