400+ open models on Hugging Face, converted to LiteRT, Core AI and ExecuTorch and measured on phones. 163 of them in litert-community. Ex-Ultralytics.
by john-rocky
1
Run on-device LLMs through a single common API; auto-select Gemini Nano or local LiteRT-LM, stream generation, use task-specific clients and lower-level engine, conversation and embedding APIs.
#text, #swift, #llm, #kotlin-native, #kotlin-flow, #kotlin-coroutines, #jetpack, #image, #client, #apple