Nativ is a SwiftUI workspace for running models locally on Apple silicon. It bundles an mlx-vlm server and adds chat with images, image generation and editing, a model library with fit warnings for your memory, performance analytics, a system monitor, menu bar controls and local dictation.
Its local server speaks OpenAI- and Anthropic-compatible APIs, and it can set up coding agents and editors such as Claude Code, Codex, OpenCode, Zed and Cline to use your local models. It can also connect MCP servers and run saved prompts on a schedule.
It needs an Apple silicon Mac (M1 or later) on macOS 26 or newer. It's free and open source (MIT); inference runs on your Mac once a model is downloaded.
How to Get It
brew install --cask nativOfficial downloads only. MLX never re-hosts an app, and never runs a command for you.
MLX Score
Ranked against the run models locally listings, from real public data only. How the score works.
Pairs Well With
Information
- Developer
- Prince Canuma
- Category
- Run models locally
- Price
- Free (Free, with no account or subscription.)
- Your data
- Runs on your Mac
- Licence
- MIT
- Mac
- macOS 26.0 or later
- iPhone and iPad
- —
- Needs
- M1 or later
- Facts checked
- 2026-11-03
Sources
You Might Also Like
OllamaRun locally
llama.cppRun locally
LM StudioRun locally
Open WebUIRun locally
AnythingLLMRun locally
Locally AIRun locally
apfelRun locally
exoRun locally
oMLXRun locallyNativ is a product of Prince Canuma; MLX isn’t affiliated with it. Something wrong? Write to support@mlx.app.