● V1.0.1 — LATEST RELEASE

Intelligence
in a box.

Run powerful language models entirely on your Mac. Bring your own MLX models or use Apple Intelligence, all from one native chat app

Download DMG View on GitHub →
Apache 2.0 · Apple Silicon · macOS 26+ · 34 MB download
100%on-device inference
0bytes leave your Mac
20 MBMetal cache cap after load
10 HzUI flush while streaming
MLX-SWIFT-LM 3.31.4 · FOUNDATIONMODELS (MACOS 26) · APPLE SILICON
WHAT'S INSIDE

Download the app. Pick a model. Chat. No inference servers. No clients. Just local AI that feels like an app.

01 — CATALOG

A curated model catalog

Qwen, Gemma, Llama, Phi, DeepSeek — quantized for Apple Silicon. Import any MLX-compatible model from Hugging Face.

02 — SYSTEM MODEL

Apple Intelligence, built in

Zero downloads. Zero setup. Future Apple Intelligence upgrades come to MLX Chat automatically.

03 — REASONING

Thinking, disclosed

Watch reasoning models think in real time, with collapsible thinking blocks and live throughput metrics.

04 — ARTIFACTS

Artifacts, rendered live

The model writes HTML or SVG; it renders beside the chat in a sandboxed web view. Markdown, syntax highlighting, and LaTeX included.

05 — STORAGE

An honest model manager

Download with progress and cancel. Delete cleanly. Disk usage that adds up. Everything lives in ~/Models, in the open.

06 — MEMORY

Auto-Unload After

Idle models automatically give memory back after 2 minutes, 10 minutes, an hour, or never. When they're unloaded, the memory actually comes back.

TWO ENGINES · ONE PROTOCOL

One model in RAM.
Behind one protocol.

ENGINE 01 — MLX

Local weights, unified memory.

Quantized models load straight into Apple Silicon's unified memory and stay hot between turns.

  • KV-cached ChatSession reused across turns — no re-prefilling the conversation
  • History trimmed to 70% of the context window before prefill
  • Metal buffer cache capped at 20 MB — no gigabytes parked after unload
ENGINE 02 — APPLE INTELLIGENCE

The OS is the model manager.

The FoundationModels framework hands MLX Chat the system's on-device model. Nothing to ship, nothing to download, nothing to babysit.

  • Transcript-seeded LanguageModelSession, fresh per turn
  • Context-window and guardrail errors mapped to human messages
  • Asks the OS for its context size — future Apple models are a free upgrade
BOTH ENGINES — ONE MENU

Switch engines mid-thought.

Apple Intelligence and your local models share one picker. Choose a model and it starts warming immediately — by the time you've typed the next message, the weights are hot.

  • One click from Apple Intelligence to any downloaded model
  • Switch-warming loads ahead of your next send, confirmed with a quiet "Switched to …" toast
  • Download Models… lives right in the menu — no settings detour
GET STARTED

Up and running
in two minutes.

Download the DMG or build from source. On Apple Intelligence–enabled Macs, chat works the moment the app opens — no model download needed.

macOS App Recommended

Drag to Applications. Chat with Apple Intelligence out of the box, or pull a local model from the built-in catalog.

Download DMG

From source

Requires an Apple Silicon Mac, macOS 26 with Xcode 26, and XcodeGen. 

# clone and generate
git clone https://github.com/abayomipopoola/mlx-chat
cd mlx-chat && xcodegen generate

# build (mlx-swift ships a plugin + macros)
xcodebuild -scheme MLXChat -configuration Release \
  -skipPackagePluginValidation \
  -skipMacroValidation build