A Quarter of the Size But Full Quality Recovery

Nexa AI's 2024 Milestones and Highlights at a Glance

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

Transforming On-Device AI with Multimodal Capabilities

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

Run Qwen2-Audio on edge devices with Nexa SDK

End-to-end Local RAG System Powered by AMD Hardware

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

Voice-Enabled Personal AI Assistant Run Entirely on Lenovo AI PC

AI Agent System Automates Influencer Discovery, Outreach and Campaign Management

LLM OS Empowering Seamless, Private, and Lightning-fast Interaction Across Mobile Apps

Nexa AI Partners with PIN AI to Bring Secure, On-Device AI to Mobile

A practical exploration of on-device AI for chatting with document: from basic Q&A to specialized tasks with LoRA

Run Multimodal AI Models on Your Local Devices