Works with both text and multimodal models and can be deployed on any devices

Compact text-audio-in model with optimized performance and size for edge devices

Pocket-size multimodal model with 9x token reduction for on-device deployment

Compact (Sub-Billion) Multimodal Action Model for On-Device AI Agents

Revolutionizing On-Device Language Models for Long Contexts

On-Device 0.5B LLMs, Voice/Text in, action out, outperform GPT-4 in function-calling

A 3.8B Model for AI Agent Action Planning with 98%+ Accuracy