Skip to main content
NexaSDK banner NexaSDK lets you run any AI model locally on NPUs, GPUs, or CPUs - easiest to use, most flexibile, and with best performance. NexaSDK is powered by NexaML engine, our unified inference engine built from scratch at the kernel level. It is capable of Day-0 support for new model architectures (LLMs, multimodal, audio, vision). NexaML supports 3 model formats: GGUF, MLX, and Nexa AI’s own .nexa format.

​
Why NexaSDK

FeatureNexaSDKOllamallama.cpp
NPU support🟢 NPU-first 🔴🔴
Day-0 support for model formats (GGUF, MLX, NEXA)🟢 Support Any Model Day-0🔴🟡
Full multimodality🟢 Image, Audio, Text🟡🟡
Cross-platform support🟢 Desktop, Mobile, Automotive, IoT🟡🟡
One line of code to run🟢🟢🟡
OpenAI API + Function calling🟢🟢🟢
Legend: 🟢 Full support  |  🟡 Partial or limited  |  🔴 Not supported

​
Get Started

Quickstart

Easily install NexaSDK and run your first model in minutes.

API Reference

In-depth documentation for all NexaSDK API.

Python Library

Learn how to use NexaSDK from Python with full code examples.

Mobile

Get started with NexaSDK for Android, iOS, and embedded platforms.

​
Community

Join Discord

Connect with the Nexa community, get support, and stay up-to-date on Discord.

Join Slack

Join our Slack workspace to collaborate, ask questions, and connect with the Nexa team.

⌘I