DEV Community: Layla

How to Replace Google Gemini with a local LLM as Your Phone's Default Assistant

Layla — Wed, 29 Apr 2026 08:15:37 +0000

Your Android phone ships with Google Gemini as the default assistant. Long-press the power button, and your voice query hits Google's servers, gets processed alongside your account data, and returns a response shaped by whatever content policies are in effect this week.

But here's the thing — Android lets you swap that default. And as of Layla v6.1.0, you can replace Gemini with a fully offline, on-device AI assistant that never phones home.

This takes about 30 seconds. Here's how.

Why Replace Gemini?

Google's assistant works fine for weather checks and timers. But it comes with trade-offs that developers and privacy-conscious users increasingly don't want to make:

Every query goes to Google's servers. Your voice data, your context, your location — all of it.
Content filtering you can't control. Gemini decides what it will and won't help you with.
Requires an active internet connection. No signal? No assistant.
Tied to your Google account. Your assistant usage becomes part of your advertising profile.

Layla flips all of this. It runs a local language model on your device's processor. Nothing leaves your phone. No account required. No filters. Works in airplane mode.

If you've been following the on-device AI space — llama.cpp, ExecuTorch, QNN acceleration on Snapdragon — Layla packages all of that into a single app with a clean UX that non-technical users can also pick up.

The Setup (Android)

This works on Samsung, Pixel, and most Android devices running Android 12+.

Step 1: Open Settings

Step 2: Search for "digital assistant" in the settings search bar

Step 3: Tap on Digital assistant app (under the Apps section)

Step 4: Change the default assistant from Google to Layla

That's it. The next time you long-press your power button (or use whatever gesture your phone maps to the assistant), Layla launches instead of Gemini.

Samsung users: Here's Samsung's official guide for changing the default assistant if you need more detail: Samsung Support — Change Default Assistant

Here's a demo of Layla launching as the default assistant:

Bonus: Set a Default Character

Here's where it gets interesting for anyone who's customized their Layla setup.

You can set a default character in Layla, so the assistant that launches on the power button press isn't just generic Layla — it's whatever personality you've configured. A technical assistant tuned for code questions. A creative writing partner. A custom character you built from scratch.

This effectively turns your phone's hardware assistant button into a shortcut to your own personalized AI — running entirely on your device.

What You Need

If you haven't installed Layla yet:

Android: Google Play or Direct APK (free version)
iOS: App Store (Note: iOS doesn't support changing the default assistant at the OS level the same way Android does)
Hardware: 6GB+ RAM recommended, any ARM64 phone from the last 4–5 years
Model: Download at least one on-device model during Layla's onboarding — a 1B–3B parameter model works well for quick assistant queries

If you want the full rundown on what Layla can do beyond just acting as your default assistant — agents, Python scripting, Stable Diffusion, Live2D characters, multi-model support — check out my previous post:

Layla

Apr 23

How to Run a Private AI Assistant on Your Phone in 2026 (Offline, No Account, No Filters)

#ai #android #ios #privacy

Comments

5 min read

The Bigger Picture

The default assistant on your phone is the most intimate software interaction you have. It's the thing you talk to when you need a quick answer, when you're thinking out loud, when you're drafting something sensitive.

Google, Apple, and Samsung all want that position because it's a firehose of behavioral data. Replacing the default with something that runs locally and keeps zero telemetry is a small change with outsized implications for your privacy.

It takes 30 seconds. Try it.

Links:

How to Run a Private AI Assistant on Your Phone in 2026 (Offline, No Account, No Filters)

Layla — Thu, 23 Apr 2026 16:24:05 +0000

Your phone's processor can run a 7-billion-parameter language model. It can generate images with Stable Diffusion. It can execute Python scripts and run autonomous AI agents — all without touching a server. Most people don't know this because the default AI experience in 2026 is still "sign up, pay monthly, send your data to the cloud."

Layla is an AI app that does all of this on your device. No internet after the initial download. No account. No data leaving your phone. This guide walks through what Layla can do, how to set it up, and what to expect on your hardware.

Google Play | App Store | Direct APK (free version)

What You Need

Minimum hardware: Any Android or iOS phone from the last 4–5 years with at least 6GB of RAM and an ARM64 processor. You can start with smaller models that fit comfortably in memory.

Recommended hardware: 8GB+ RAM, Snapdragon 8 Gen 2 or newer (or Apple A16+). This opens up 3B–7B parameter models where output quality gets genuinely useful.

What you're trading vs cloud AI: Cloud models like ChatGPT and Claude run hundreds of billions of parameters on data center hardware. Your phone runs 1B–7B parameter models. You lose some depth on complex reasoning tasks, but for everyday use — quick questions, brainstorming, drafting, conversation, creative writing — on-device models are surprisingly capable. And nothing you say ever leaves your phone.

What Layla Can Do

Layla isn't a bare-bones chat wrapper around llama.cpp. It's a full AI platform running on your device.

Text generation with multiple model backends. Layla supports GGUF models (via llama.cpp), LiteRT-LM models, and PTE models (via ExecuTorch) in a single unified interface. Load whichever model format works best for your hardware.

On-device image generation. Layla runs Stable Diffusion 1.5 models directly on your phone. It supports importing custom safetensor models from CivitAI, and on Snapdragon devices it can run QNN models on the NPU for faster generation. Images generate during chat for a more immersive experience.

Agents. This is where Layla gets interesting. You can run autonomous AI agents right on your phone — agents that read the news, research topics, run "choose your own adventure" stories, and more. You can create and customize your own agents directly in the app.

Python scripting. Layla supports executing Python scripts on-device. You can write Python code that augments Layla's agentic capabilities, chaining together custom logic with the LLM.

Live2D characters. Import custom Live2D models as your AI character. Lip movements, expressions, and animations sync with chat responses in real time.

Downloadable characters. Browse and download community-created personalities from Layla's Personality Hub. Every character runs entirely locally once downloaded. You can create your own and share them anonymously.

Multi-character roleplay. Create scenarios with multiple AI characters. You can participate as a character yourself and steer the story in any direction. Everything stays on your phone.

Tailored Use Cases

When you first open Layla, you choose how you want to use it. This isn't just a theme selector — it configures the system prompt, features, and interaction style for your use case:

Personal assistant — scheduling help, quick lookups, task management
Creative partner — story writing, brainstorming, idea generation
Roleplay companion — character-driven conversation with full creative freedom
Technical assistant — code help, document analysis, research

You can switch between these at any time, and you can extend Layla's capabilities by adding "mini-apps" — self-contained feature modules that the team ships weekly. These range from horoscope checks to local text-to-speech with 100+ voices.

Loading Your Own Models

If you're a local LLM enthusiast, Layla gives you full control. You can:

Import any .gguf model file from your device storage
Adjust temperature and other generation parameters
Configure context length and sampling settings
Switch between CPU, GPU, and NPU execution paths

This means if you have a favourite model from HuggingFace already downloaded, you can point Layla at it and start chatting immediately.

Hardware Acceleration

Layla automatically detects your hardware and picks the fastest execution path:

Snapdragon with QNN: If your phone has a Snapdragon 8 Gen 1 or newer, Layla can offload inference to the dedicated Neural Processing Unit. This is significantly faster and more power-efficient than CPU or GPU inference. It also accelerates Stable Diffusion image generation.

GPU via OpenCL: Available on most Snapdragon-equipped Android phones. Faster than CPU alone, and a good fallback for older hardware.

CPU: Works on everything. Slower, but perfectly usable for 1B–3B models.

Apple Metal: On iOS, Layla can leverage Apple Metal for accelerated inference.

Privacy: What "Offline" Actually Means

After you download the app and your chosen model, Layla makes zero network requests. You can put your phone in airplane mode and use every feature. The AI runs on your device's processor. Your conversations are encrypted and stored locally. You can delete everything at any time.

Features that do require an internet connection — like downloading new characters from the hub — are clearly marked in the UI. Layla asks for explicit consent before any data is transmitted. This isn't a privacy policy buried in legal text. It's a design principle enforced at the architecture level.

For sensitive conversations — medical questions, legal notes, personal journaling, work discussions involving proprietary information — on-device AI eliminates the tradeoff between capability and privacy.

Getting Started

Install Layla from the Google Play Store, App Store, or grab the Direct APK (free version with limited features)
Choose your use case during onboarding
Download a recommended model for your device's RAM
Turn on airplane mode to verify everything works offline
Start chatting

The full app is a one-time purchase — no subscription. The direct APK offers a free version with limited features so you can try before you buy.

What Makes Layla Different

The on-device AI space is growing fast, but Layla stands out in a few ways:

It's a platform, not just a chat app. Between agents, Python scripting, Live2D characters, Stable Diffusion, multi-character roleplay, and the mini-app system, Layla is closer to a local AI operating system than a simple chatbot.

Multiple model backends. Supporting GGUF, LiteRT-LM, and ExecuTorch in one app means you're not locked into a single inference engine. Use whatever runs best on your hardware.

Active development with community input. The developer is highly responsive on Discord, shipping updates weekly and incorporating user feedback directly. This isn't a side project — it's evolving fast.

No filters. Because the model runs on your hardware, there's no content moderation layer between you and the AI. Your imagination is the limit. With great power comes great responsibility.

The Bigger Picture

A year ago, running a useful AI model on a phone felt like a novelty. Today, 7B models run at usable speeds on mid-range hardware, on-device image generation is real, and apps like Layla are shipping agent frameworks and Python runtimes that turn your phone into a genuine AI development environment.

The trajectory is clear. Hardware keeps getting faster. Models keep getting more efficient at smaller sizes. The gap between cloud and on-device AI narrows every quarter.

Layla is betting that the future of AI is personal, private, and runs in your pocket. Based on what it can do today, that's not a bad bet.

Links: