AI Tool Atlas

Chat assistantsDocumented overviewLast checked Oct 1, 2026

Private LLM: Pricing, Features & Best Use Cases

Offline AI chat app for iPhone, iPad and Mac that runs open-source models on-device with a one-time purchase.

Private LLM homepage screenshot, chat assistants AI tool

Our take: Private LLM suits privacy-minded iPhone, iPad and Mac owners who want open-source chat models running entirely on-device after a one-time purchase, with Siri and Shortcuts integration.

Main limitation: It runs only on Apple devices, needs a large model download first, and performance depends on your device's hardware.

By the AI Tool Atlas editors. Based on the vendor's official documentation; we have not tested this product hands-on. What “documented overview” means

Who Private LLM fits

Private LLM suits privacy-minded iPhone, iPad and Mac owners who want open-source chat models running entirely on-device after a one-time purchase, with Siri and Shortcuts integration. Based on the vendor's documentation, not on a hands-on test.

Best for: Privacy-focused users

Also a good fit for

  • Apple device owners
  • Offline use

Consider another tool if apple devices only

Or if

  • Model download needed first
  • Performance depends on device hardware

Private LLM pricing and usage limits

Prices checked Oct 1, 2026 on the official US pricing page. Prices and limits change often.

Free access and trial conditions

Not stated on fetched pages.

Not stated.

Paid plans: what changes as you upgrade

One-time purchase app store

See official pricing

One-time

For: Individuals and families on Apple devices

Limits

  • Family Sharing for up to six people

Includes

  • Unlocks iPhone, iPad and Mac
  • No subscription
1 more
  • No account

No API

Usage caps, credits and extra costs

No subscription; the App Store price was not visible on the fetched pages.

Handled by Apple.

What is Private LLM, and how does it work?

Private LLM runs open-source language models such as Llama, Qwen, Gemma and DeepSeek distills locally on Apple devices, with no account and no internet needed after the model download. It integrates with Siri and Apple Shortcuts and offers on-device writing tools in macOS. It is sold as a one-time App Store purchase with Family Sharing.

Private LLM homepage — screenshot of the chat assistants AI tool, Oct 1, 2026
Private LLM's official site: how the product presents itself. privatellm.app, captured Oct 1, 2026

What you provide and what you get back

How Private LLM works: what you provide, where it runs and what you get backYOU PROVIDEYour inputTyped promptsSelected text in macOS appsSiri and Shortcuts triggersCHAT ASSISTANTSPrivate LLMDesktop, Mobileprice not publishedno free tierchecked Oct 1, 2026YOU GET BACKThe resultOn-device chat repliesRewritten, summarized or correcte…Responses piped into other apps v…input → Private LLM → output · from the vendor's own pages, no hands-on test unless stated
What you give Private LLM and what comes back, from its documentation

You provide

  • Typed prompts
  • Selected text in macOS apps
  • Siri and Shortcuts triggers

You get back

  • On-device chat replies
  • Rewritten, summarized or corrected text
  • Responses piped into other apps via x-callback-url

Where you can use it

Platforms
Desktop, Mobile
Account
Not required
Models / versions
140+ local models: DeepSeek R1 Distill, Llama 3.3 70B, Qwen3 4B, Phi 4, Gemma 3
Platforms
iPhone, iPad, Mac
Models
140+ open-source models
Quantization
OmniQuant and GPTQ
Languages for macOS tools
English and major Western European languages

Where Private LLM is most useful

Scenarios are worked out by our editors from the documentation; the actual result depends on your input and plan.

Offline private chat

Who
Privacy-conscious users
You provide
Questions typed into the app with no internet
Expected result
Private chat that never leaves the device
Plan needed
One-time purchase
Limitation
Downloads of large models are needed first source (opens in a new tab)

Writing help on macOS

Who
Mac writers and professionals
You provide
Selected text in any macOS app
Expected result
Rewritten, summarized or corrected text via right-click
Plan needed
One-time purchase
Limitation
Supports English and major Western European languages source (opens in a new tab)

Apple Shortcuts automation

Who
Shortcuts power users
You provide
A Shortcut that calls Private LLM
Expected result
AI workflows feeding 70+ apps via x-callback-url
Plan needed
One-time purchase
Limitation
Workflows depend on the Shortcuts app source (opens in a new tab)

Key features and their practical limits

Private LLM homepage — screenshot of the chat assistants AI tool, Oct 1, 2026
Feature overview on the official site. privatellm.app, captured Oct 1, 2026

On-device inference

Runs models entirely on the iPhone, iPad or Mac with no cloud processing. Keeps conversations private.

Access: AppLimit: Speed depends on device hardware. source (opens in a new tab)

140+ models listed

Offers a catalog including DeepSeek R1 Distill, Llama 3.3 70B, Qwen3 4B, Phi 4 and Gemma 3. Lets you pick a model for your device.

Access: AppLimit: Larger models need more RAM. source (opens in a new tab)

OmniQuant/GPTQ quantization

Uses OmniQuant and GPTQ builds tuned per model, claimed to match 4-bit quality at 3-bit. Fits bigger models into less memory.

Access: AppLimit: Quality claims are the vendor's. source (opens in a new tab)

Siri and Shortcuts

Plugs into Siri and the Shortcuts app and supports the x-callback-url specification. Automates writing and summarizing without code.

Access: AppLimit: Needs Shortcuts configuration. source (opens in a new tab)

macOS writing tools

Right-click selected text in any app to rewrite, summarize or correct it on-device. Brings AI editing to every Mac app.

Access: macOS appLimit: Mac only. source (opens in a new tab)

Pros, cons and deal-breakers

Reasons to choose Private LLM

Check before paying for Private LLM

How to use Private LLM for running a private AI chat offline

Set up Private LLM

  1. Install Private LLM from the App Store on your iPhone, iPad or Mac.
  2. Open the model browser and pick one suited to your device's RAM.
  3. Download the model while online.
  4. Switch to airplane mode to confirm it works offline.

Example: running a private AI chat offline

  1. Start a new chat with the downloaded model.
  2. Ask it to summarize a pasted paragraph.
  3. On a Mac, select text in another app and right-click to rewrite it.
  4. Create a Shortcut that sends clipboard text to Private LLM.

Review and export the result

  1. Confirm responses arrive with Wi-Fi off.
  2. Check memory use and speed on a larger model.
  3. Test the Shortcut returns the output to the target app.
Example prompt suggested by our editors (not a recorded output of the product)
Summarize the following meeting notes into five bullet points and list any action items.

Private LLM API

API access and separate billing

Private LLM has no public API in its official documentation. No API; automation is through Shortcuts.

Privacy, data use and commercial rights

Summarized from the vendor's current policies; this is not legal advice and a vendor's badge is not an independent audit.

How your inputs and outputs are handled

Conversations stay on the device; the site claims no account, tracking or logs.

Not applicable as models run locally.

Data stays on your device.

Private LLM alternatives by need

"Better suited" is based on documented features and pricing, not on a head-to-head test.

ChatGPT: better suited to

Alternatives
AlternativeWhen to choose itPricingLimitation
ChatGPT——Compare

Explore Private LLM further

Best AI chatbot toolsOur picks in this category, compared by price and free tiers.Prompts for Private LLMReady-to-copy prompts with their sources.

If you are looking at Private LLM

Private LLM user reviews

No user reviews yet.

Used Private LLM? Be the first to share your experience.

Write a review

Reviews are checked by a moderator before they appear. Your email is never published. Plain text only.

Your rating (required)

Show what you made or what went wrong. Images are published only if the review is approved; location data is removed.

    Private LLM FAQ

    Does Private LLM need an internet connection?

    Only for the first model download; after that no internet is required. source (opens in a new tab)

    Is there a subscription?

    No. It is a one-time purchase that unlocks iPhone, iPad and Mac, with Family Sharing for up to six people. source (opens in a new tab)

    Which models can it run?

    Over 140 open-source models, including DeepSeek R1 Distill, Llama 3.3 70B, Qwen3, Phi 4 and Gemma 3. source (opens in a new tab)

    Can I use it with Siri and Shortcuts?

    Yes, it integrates with Siri and Shortcuts and works with 70+ apps supporting x-callback-url. source (opens in a new tab)

    Do I need an account?

    No. The site says no account, tracking or logs. source (opens in a new tab)

    Sources and review methodology

    Official sources and verification dates

    Not verified: App Store price; Privacy policy (404); Minimum device requirements per model.

    How we documented and maintain this page

    Every fact about Private LLM above comes from the 3 official pages listed here, last compared on Oct 1, 2026; we have not run Private LLM ourselves, so it has no editorial score. How we check and re-check pages.

    Article updated Oct 10, 2026; prices checked Oct 1, 2026. Outbound links to vendors are plain links; we do not earn commissions. How we review · Report an error