The main on-device LLMs in 2026 are Gemma 3n, Qwen 3.5 Small, Llama 3.2, Phi-4-mini, Ministral 3, and SmolLM3. Sub-3B quantized models can hit 30-50 tokens/sec on phones with 8GB RAM, but RAM, thermal throttling, and context window remain hard constraints.
OpenClaw's iOS and Android apps are not Gateways — they are Nodes, turning your phone's camera, screen, location, and voice into sensory extensions for AI agents.
Expo turns React Native development from 'environment setup hell' into a state where you can just start writing logic. Expo Router brings file-based routing that dramatically lowers the barrier for web developers making the switch. Both DaoDao and NobodyClimb use it to ship across iOS and Android.