This quickstart will walk you through how to install nexaSDK and run your first models on device.

​
Installation

Download Here:
arm64
x86_64

​
Running Your First Model

MacOS supports both MLX and GGUF model formats. Currently, we support LLM and Multimodal models. More model type support is coming soon!
Language Model (LLM)
MacOS
nexa infer NexaAI/Qwen3-4B-4bit-MLX
Multimodal Model
MacOS
nexa infer NexaAI/gemma-3n-E4B-it-4bit-MLX
Many MLX models in the Hugging Face mlx-community have quality issues and may not run locally. We recommend using models from our collection for best results.

​
Explore CLI Commands

To see a list of all available CLI commands, run:
MacOS
nexa -h