Noema running locally across a Mac and iPhone

Native on iPhone, iPad, Mac, and Vision Pro

Private intelligence,entirely yours.

Run advanced models, search your own files, and use real tools without giving up your conversations.

Download on the App Store

Current releaseNoema 3.6

The privacy model

Local by default.

0cloud required for local chat

Local chats can remain on your device.

Optional network routes are visibly controlled.

Off-grid Mode blocks external HTTP and HTTPS.

One private system, wherever you think.

Current product surfaces. Real local models.

Noema model library showing local and support models on Mac and iPhone

Load local models, Apple Foundation Models, and support models from one native library.

Introducing Constellation

Switch devices mid-chat. Borrow your Mac's models.

Chats, projects, and tool history stay in step across your Apple devices. Pick a model installed on your awake Mac and run it from your iPhone or iPad — the weights never leave the Mac, only the request and the reply.

Explore Constellation

MacBook Pro7 models · ready

iPhoneChat continues

iPadSame project

Local Network · connected

A complete local AI workspace.

Run local models

GGUF, MLX, Core ML, ExecuTorch, and Apple Foundation Models in one native client.

Work from your files

Read PDFs more thoroughly and ground answers in your own datasets with retrieval that stays on device.

Use real tools

Open web evidence, inspect citations, and connect MCP tools when the task needs them.

Reach your Mac

Continue chats across devices and use the models installed on your awake Mac through Constellation.

Noema's first model

Small enough for the edge. Built to reason with less.

Noema 2B is a 2-billion-parameter model tuned for token-efficient reasoning, mathematics, and clear instruction following on personal hardware.

Explore Noema 2B

Parameters: 2 billion
Base: Qwen3.5-2B
Released: July 2026

Your models. Your files. Your device.

No subscription. No cloud dependency.

Get Noema