Run AI modelslocally on your Mac.

blaizzy.github.io · 2026-07-22 · by Long Nguyen ·generic
Nativ runs open language, vision, video, code, and embedding models locally on Apple Silicon. Free, private, and open source.

Run AI modelslocally on your Mac.

Latest release · 100% open source · live now

Run AI models

locally on your Mac.

Nativ puts frontier intelligence on your desk. Download and run open models on Apple Silicon — no accounts, no subscriptions, no cloud.

Download for macOS↘ Join the Discord ↗

Universal · Apple Silicon (M1+)

WE ARE 100% OPEN SOURCE · MIT LICENSED · ✦

Nativ, running on macOSReal app. Real local models. No cloud.

Chat Analytics Models Integrations

Nativ chat running the Gemma 4 model locally, with response token and memory telemetry

01 / CHAT

Talk to open models with streaming responses and per-message performance metrics.

CAPTURED LIVE ON THIS MAC · JUL 2026

/ SIX REASONS TO GO LOCAL

Everything you need.

Nothing you don’t.

01CURATED LIBRARY

Pick the right model for your Mac

Run standout open models from Google, Cohere, and Liquid AI. Nativ recommends the right partner model for your hardware.

Gemma 4 E2BGoogle · 10.28 GB_128K_

North Mini CodeCohere · 19.38 GB_500K_

LFM2.5-VL 1.6BLiquid AI · 3.20 GB_128K_

02CHAT

Prompt it like you would Claude

A clean interface with streaming, markdown, code highlighting, and image input. Every response is generated locally.

Explain this repository

03TELEMETRY

See what’s actually happening

Live tokens/sec, memory pressure, thermal state, and time-to-first-token. The details developers want.

04APPLE SILICON

Optimized for Apple Silicon

Built on MLX-VLM and tuned for M-series unified memory and Metal — no wrappers, no translation layers.

MLXUNIFIED MEMORY

05EVERY MODALITY

Language, vision, video, code, audio

Chat with an LLM, caption an image, summarize video, autocomplete code, or transcribe and generate speech.

TXTIMGVID⌘\_AUD

06FREE FOREVER

Not a SaaS.

Not a subscription.

No accounts to create, no credits to buy, no data to sell. You own it end-to-end.

MITLICENSED

/ INTEGRATIONS

Your tools.

Your models.

Connect the coding agents you already use to models running locally on your Mac. Nativ handles the endpoint; your workflow stays familiar.

01Pi 02Codex 03Claude Code 04Hermes 05OpenCode

Nativ integrations screen showing Pi, Codex, Claude Code, Hermes, and OpenCode configured to use local models

LOCAL ENDPOINT One model server. Every coding agent.

MANIFESTO · REV 1.0

Why we’re open source

when nobody else is.

`philosophy.txt`UTF-8

$ cat philosophy.txt

The other “local AI” apps you’ve heard of? They’re proprietary shells built on top of open-source engines they don’t own. They keep the UI closed, add a paywall, and hope you don’t look under the hood.

We built in the open. The desktop app is open too. Every line. Every model loader. Every telemetry chart. You can read it, fork it, or send a pull request tonight.

No VC roadmap. No enterprise tier. No dark pattern that turns your prompts into training data. Just software made by researchers and hackers, for researchers and hackers.

// Community owned. MIT licensed. Free forever.

MODELCREATORCONTEXTSIZETYPE

Gemma 4 E2B InstructGoogle128k10.28 GB_VISION + AUDIO_↗ North Mini CodeCohere500k19.38 GB_CODE + TOOLS_↗ LFM2.5-VL 1.6BLiquid AI128k3.20 GB_VISION + LANGUAGE_↗

Explore the full model library →

NATIV

YOUR MAC IS MORE CAPABLE THAN YOU THINK

Stop renting

intelligence.

Run it locally, in the open.

Download for macOS ↘ View source ↗

100% OPEN SOURCE_✱MIT✱RUNS ON YOUR MAC✱NO ACCOUNTS✱100% OPEN SOURCE✱MIT✱RUNS ON YOUR MAC✱NO ACCOUNTS✱_

blaizzy.github.io · 6 images · 12 links

Comments (0)

No comments yet