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

​
Installation

Download Here:
arm64 with Apple Neural Engine support
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!
  • MLX Models
  • GGUF Models
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

⌘I