# What is a local AI assistant?

> What is a local AI assistant? How on-device AI works, what stays on your device, what can still go online, and how to check privacy and speed.

Canonical: https://askloci.ai/local-ai-assistant/
Last updated: 2026-11-15

Local AI, explained

Last updated: 2026-11-15

A local AI assistant runs the language model on your own device, so ordinary prompts can be answered without a round trip to a hosted AI server.

## The direct answer

A local AI assistant is an app that runs its language model on the phone, tablet, or computer in front of you. The prompt does not need to travel to a provider's AI server before the model can answer.

“Local” describes the inference path. It does not automatically make every feature offline, private, accurate, or unlimited.

## The four distinctions worth remembering

- A local interface is not enough; the model itself must run on the device.
- Offline inference and optional online tools can coexist in the same app.
- Privacy depends on diagnostics, accounts, syncing, and search as well as where the model runs.
- The best model is the one that fits the device and the task, not the largest download.

## How a local AI answer is produced

Each step is something you can check for yourself.

### 1. Download the model weights

A language model is stored as one or more files. A local assistant must put those files on the device before it can use them offline.

### 2. Load the model into memory

The app prepares the model using the device's processor, graphics hardware, and available memory. Larger models need more resources.

### 3. Process the prompt locally

The app turns your words, or supported images and files, into input the model can interpret without sending them to a remote inference service.

### 4. Generate the reply on the device

The model produces the answer token by token. A connection is unnecessary unless the task invokes a separate online feature such as web search.

## Local AI and cloud AI take different routes

A cloud assistant cannot answer until the provider receives the prompt. A local assistant can send the same prompt to a model already loaded on the device.

Local AI compared with a hosted cloud assistant

| What matters | Loci | Cloud AI |
| --- | --- | --- |
| Where the model runs | On your own phone, tablet, or computer. | On computers operated by the provider. |
| Ordinary chat path | Prompt → local model → reply. | Prompt → network → provider → network → reply. |
| Works without signal | Yes, after the model is downloaded. | No. Every answer needs a connection. |
| Live information | Requires a separate online search. | May be integrated, but still depends on online services. |
| Practical limit | Device memory, storage, heat, and model size. | Provider limits, pricing, availability, and data policy. |

## Local is an architecture, not a magic label

An app can run its main model locally and still use the internet for other reasons. That is not inherently deceptive. The problem begins when those reasons are hidden behind a blanket claim that “nothing ever leaves.”

Questions that reveal what “local” really means

| Ask this | A strong answer sounds like | Why it matters |
| --- | --- | --- |
| Where does inference happen? | On this device, using a named local model or runtime. | This determines whether ordinary prompts need a hosted AI server. |
| What works after disconnecting? | Core chat and a specific list of supported inputs. | “Offline” should describe usable behavior, not merely an app that opens. |
| What diagnostics are collected? | A precise list, a clear exclusion of content, and an off switch. | Local inference does not prevent separate analytics collection. |
| What happens during web search? | The destination, the exact data sent, and whether conversation context is included. | An online lookup creates a separate privacy boundary. |
| How are models chosen? | By device memory, storage, capabilities, and the intended task. | An unsuitable model can be slow, unstable, or impossible to load. |

## How to audit a local AI assistant in five minutes

1. **Find the model.** The app should identify what is downloaded or connected locally.
2. **Disconnect the device.** Start a new conversation, not just a cached follow-up.
3. **Test the inputs you care about.** Text may be local while files, images, or voice follow a different path.
4. **Read the privacy policy by feature.** Look separately for chat, diagnostics, search, downloads, syncing, and support.
5. **Check the failure behavior.** When current information is unavailable, the app should say so rather than invent a live answer.

**A useful rule:** the offline test proves that inference can happen locally. It does not replace a data-flow disclosure, and a privacy policy does not replace the offline test. You need both.

## Where local AI is strongest

### Good reasons to choose local

- Private drafting, notes, files, or personal questions.
- Flights, travel, dead zones, and unreliable networks.
- Predictable access without per-message charges.
- Control over which model is installed and used.
- Everyday writing, summarizing, coding, and planning.

### Reasons to choose cloud

- Frontier-scale reasoning is more important than privacy.
- The task needs extensive, current web research.
- The device lacks the memory for a capable local model.
- You need a large shared knowledge base or cloud collaboration.
- You accept the provider's account, retention, and pricing terms.

## How Loci fits the definition

Loci runs AI models on Android, iPhone, iPad, Mac, and Windows. Every platform downloads open models, including Gemma, Qwen, Llama, and Phi. On Apple devices it can also use Apple's built-in foundation model, depending on the device and selected model.

Core chat and model inference stay on your device. Web search and live information go online: your settings decide whether Loci looks things up when a question needs current information or only when you ask. When it does, your device sends a search drawn from what you asked straight to the service that answers it, and for weather, scores and similar questions only what the request needs, such as a place. Loci may also open a few of the pages it finds, much as a browser would. Those services and websites see ordinary connection details such as your IP address. None of it passes through a Loci server, and your files and the rest of your chat history are not sent. The [Privacy Policy](https://askloci.ai/privacy/) explains what each online feature sends.

## Questions about local AI assistants

### What is a local AI assistant?

A local AI assistant runs its language model on your own device. Prompts can be processed and replies generated without sending ordinary chat to a remote AI server.

### Is every local AI assistant completely offline?

No. Local inference can work offline while separate features, such as model downloads, web search, syncing, or diagnostics, still use the internet. Each data flow should be evaluated independently.

### Does local AI automatically mean private AI?

Not automatically. Local inference removes the need to send prompts to a hosted model, but an app can still collect other data. A trustworthy product explains diagnostics, online tools, accounts, and storage separately.

### Why are local models smaller than cloud models?

They have to fit into the memory and storage of one device. Cloud systems can spread much larger models across specialized servers, while local models are optimized to run within a personal device's limits.

### Can local AI search the web?

Yes, if the app offers a separate search feature and the device is online. The search request is no longer fully offline, so the app should disclose where that query goes and what context is included.

### How can I tell whether an AI app is actually local?

Download its model, disconnect the device, and start a new conversation. Then inspect the privacy policy for diagnostics, search, sync, and account behavior. The offline test proves local inference; the policy explains the remaining data flows.

### Which local AI assistant can use tools?

Loci can. It searches the web when a question needs it, reads documents you add, understands images, takes dictation and remembers what you tell it, from one app with no account. On Mac it also reaches email, calendar and reminders, and the direct download serves a local API so coding agents such as Claude Code and Codex can use the model on your machine.

## See the architecture in practice

- [Run the airplane-mode test on an iPhone](https://askloci.ai/offline-ai-iphone/)
- [Trace every data flow on a Mac](https://askloci.ai/private-ai-mac/)
- [Get Loci for Android](https://play.google.com/store/apps/details?id=app.lociai.loci)
- [Understand why local chat changes the privacy boundary](https://askloci.ai/private-ai/)
- [See what owning a downloaded model changes](https://askloci.ai/offline-ai/)
- [See how fast local models run on each phone and Mac](https://askloci.ai/speed/)
- [Find what fits in 8, 16 and 32 GB](https://askloci.ai/guides/best-local-llms/)
- [Start from zero: how to run an LLM locally](https://askloci.ai/guides/run-llm-locally/)
- [New to the idea? What local AI is, in plain terms](https://askloci.ai/guides/what-is-local-ai/)

## Product details

- [Loci privacy policy and exact data flows](https://askloci.ai/privacy/)
- [Loci for Android on Google Play](https://play.google.com/store/apps/details?id=app.lociai.loci)
- [Loci for iPhone and iPad on the App Store](https://apps.apple.com/app/id6762100748)
- [Loci for Mac on the Mac App Store](https://apps.apple.com/us/app/private-local-ai-loci/id6768186318?mt=12)

