On-device Gen AI inference runtime for Qualcomm Snapdragon that runs GGUF and precompiled models on Hexagon NPU, Adreno GPU, or CPU via multiple interfaces.
On-device Gen AI inference runtime for Qualcomm Snapdragon that runs GGUF and precompiled models on Hexagon NPU, Adreno GPU, or CPU via multiple interfaces.
React Native library for high-performance on-device LLM inference with LiteRT-LM and Nitro Modules, featuring crash-free memory handling and structured outputs.
On-device AI kit for Expo and React Native that runs local LLMs for streaming chat, schema-validated outputs, tool calling, and on-device embeddings with RAG.