ExecuTorch

ExecuTorch is PyTorch’s unified solution for deploying AI models on-device—from smartphones to microcontrollers—built for privacy, performance, and portability. It powers Meta’s on-device AI across Instagram, WhatsApp, Quest 3, Ray-Ban Meta Smart Glasses, and more.

https://huggingface.co/facebook/MobileLLM-Pro

Liquid Nanos

Most edge AI applications require models that excel in one particular task, such as translation or function calling. Typically, this requires fine-tuning general-purpose models for a given task. However, fine-tuning remains a challenge for many users due to a lack of time, data, or compute. To address this gap, we created a model library with a collection of task-specific LFM2 models. These specialized checkpoints offer very high-quality outputs with a tiny memory footprint. All the models in this growing library are available on Hugging Face and directly compatible with LEAP and Apollo.

Qualcomm® AI Hub Models is our collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices.

https://aihub.qualcomm.com/mobile/models

LiteRT Community

LiteRT is Google’s on-device framework for high-performance ML & GenAI deployment on edge platforms. It is the improved successor to TensorFlow Lite. On this community page, you can find ready-to-run LiteRT models for a wide range of ML/AI tasks.

pocketpal-ai

An app that brings language models directly to your phone.

MediaPipe isan open-source, cross-platform framework by Google designed for building and deploying on-device machine learning (ML) pipelines for live streaming media, including video and audio

Cactus compute

Low-latency AI engine for mobile devices & wearables

Resources