gemma 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 an LLM On-Device with LiteRT-LM: A Complete iOS Integration Tutorial Jun 27, 2026 GPU Isn't Always the Answer: Benchmarking CPU vs GPU for Small Language Models on Mobile Jun 27, 2026