01
Real-time search
Fresh answers when the world changes.
Turn on search when you need current information. Arbiter finds useful sources and brings them into your local chat.
- Current information
- Useful sources
- Search only when needed
Private AI for Apple devices
Run AI models locally on iPhone and Mac.
Chat with open models on the hardware you already own. Stay offline, choose the model that fits, and keep every conversation yours.
Private by design Works offline
What makes Arbiter different
Key features, in focus
Search, work with files, use images, and reach larger Mac models without giving up control.
02
Upload documents
Ask questions about your files.
Add a PDF or text file, then ask for a summary, key details, or a simpler explanation.
- PDFs and text
- Quick summaries
- Follow-up questions
03
Chat with images
Show Arbiter what you mean.
Send a photo or screenshot to a vision model and ask what it sees, all in the same private chat.
- Photos and screenshots
- Visual questions
- Private by design
04
Export conversations
Keep and move your chats.
Export a conversation for backup, then import it later on another device.
- Simple backups
- Easy transfers
- You keep the file
Export chatOn device
Export complete05
More power from your Mac
Use a larger Mac model from your phone.
Connect your iPhone to Arbiter on your Mac and chat with larger MLX models over your own Wi-Fi.
- Bigger Mac models
- Chat from iPhone
- Stays on your network
06
Siri integration
Ask with your voice.
Use Siri Shortcuts to send a question hands-free and continue the conversation in Arbiter.
- Siri Shortcuts
- Hands-free questions
- Continue in the app
Siri + ArbiterOn device
“Ask Arbiter to explain this in simple terms.”
Listening securely07
Roles & translation
Pick the right helper.
Switch roles for translation, studying, writing, and more. Adjust the tone and detail to fit you.
- 10 built-in roles
- Natural translation
- Your preferred tone
Translator roleOn device
English
Privacy should feel effortless.
SpanishLa privacidad debería ser sencilla.Also included
More ways to make local AI your own.
Apple Foundation Models
Use Apple’s on-device model with no additional download on eligible devices.
Local network power
Connect to Arbiter on Mac, LM Studio, Ollama, or another compatible local server.
Works offline
Keep chatting without Wi-Fi once your model is downloaded.
Smart model catalog
Compare, filter, download, and manage 44 models across open model families.
Open benchmarks
See how local models compare.
Community results make it easier to choose the right model for your device.
64questions8skill areascommunity tested
Explore all benchmarks The problem with AI today
Where cloud AI falls short
Your data leaves your device
Every prompt you send to a cloud AI is processed on someone else's servers, logged, stored, and potentially used to train future models.
Requires internet to function
Cloud AI stops the moment your connection drops. On a flight, in a dead zone, or on a slow network, you are left without assistance.
Expensive and metered
Premium AI is locked behind monthly subscriptions and per-query fees. Your usage is tracked, throttled, and billed at every turn.
See the difference
Arbiter vs. Cloud AI
Arbiter
Cloud AI
Runs locally on device
✓
✗
Works offline
✓
✗
Data leaves your device
Never
Always
Account required
No
Yes
Custom model selection
✓
Limited
Scale via local network
✓
N/A
Use your own hardware as server
✓
✗
Subscription fee
None
Required
Full privacy
✓
Partial
Common questions
FAQ
Is my data private?⌄
Yes. Everything is processed and stored on your device. Your chats and files never leave your phone or Mac unless you explicitly choose to share them. This applies across iPhone and Mac, whether running models locally or serving them on your network. Your data never touches external servers.
Do I need an internet connection to use the app?⌄
No. Once a model is installed, the app works entirely offline. You can use it on airplanes, in remote areas, or without Wi-Fi, while still getting fast and responsive answers.
How does offline AI work?⌄
Arbiter uses optimized open-source models that run locally on your device’s Apple Silicon processor. Both GGUF and MLX model formats are supported on iPhone and Mac. Models are pre-downloaded and don’t require server access, so your requests are processed instantly without sending anything to the cloud.
What devices are supported?⌄
Arbiter runs on iPhones and iPads with iOS 16 or later, with best performance on devices with A14 Bionic or newer and at least 6 GB of RAM. Arbiter for macOS is available on Apple Silicon Macs (M1 or later) and can run larger MLX models.
What AI models are available?⌄
Arbiter offers 44 models across families including Gemma, Llama, DeepSeek, Qwen, Mistral, Phi, and Granite. The catalog includes 24 GGUF and 20 MLX models, all usable on both iPhone and Mac, plus 9 vision-capable models and 10 reasoning models. On supported devices, Apple’s Foundation Model is also available.
What is Apple Foundation Model support?⌄
Starting with iOS 26 and macOS 26, Arbiter integrates Apple’s on-device Foundation Models through Apple Intelligence. These models run natively on your device at no additional cost, providing another option alongside open-source models with zero downloads required.
Can I use my Mac as a server for my iPhone?⌄
Yes. The macOS app includes a Serve Model feature that creates an OpenAI-compatible local API server. Your iPhone can connect to your Mac over Wi-Fi using automatic Bonjour discovery, letting you run larger models on your Mac while chatting from your phone.
Can I connect to other local AI servers?⌄
Yes. Beyond Arbiter’s own Mac server, you can connect your iPhone to any local machine running LM Studio, Ollama, or any OpenAI-compatible API server on your local network. Configure the host and port and you’re connected.