# LLM Server — On-Device AI API

> Run AI models on your phone and serve them as an API endpoint to any app

Canonical page: [https://chrome-stats.com/d/com.llmserver](https://chrome-stats.com/d/com.llmserver)

## Overview

- **ID:** `com.llmserver`
- **Platform:** Android
- **Type:** Android app
- **Status:** Available
- **Publisher:** magnus2026
- **Category:** PRODUCTIVITY
- **Downloads:** 12
- **Version:** 1.7.0
- **Last updated:** 2026-09-01
- **First published:** 2026-08-28
- **Publisher country:** HK
- **Size:** 191 MB
- **Data as of:** 2026-11-22
- **Store listing:** [Google Play Store](https://play.google.com/store/apps/details?id=com.llmserver)
- **Website:** [https://atrix228.github.io/llm-server/](https://atrix228.github.io/llm-server/)
- **Privacy policy:** [https://atrix228.github.io/llm-server/](https://atrix228.github.io/llm-server/)

## Description

★ Turn Your Phone Into an AI Server ★<br><br>LLM Server lets you run large language models directly on your Android device — and expose them as a local API endpoint that any app, script, or AI agent can connect to.<br><br>No cloud. No subscriptions. Your phone becomes the AI backend.<br><br>━━━━━━━━━━━━━━━━━━━━━━━━━━━━<br><br>🧠 ON-DEVICE INFERENCE<br>• Run open-weight LLMs (Llama, Gemma, Phi, Qwen, Mistral and more)<br>• Optimized for mobile hardware with GGUF quantization<br>• Full privacy — your data never leaves your device<br>• Works completely offline once models are downloaded<br><br>🔌 BUILT-IN API SERVER<br>• OpenAI-compatible REST API served from your phone<br>• Connect any tool that speaks the OpenAI API format<br>• Stream responses in real-time via Server-Sent Events<br>• Serve multiple clients on your local network<br><br>🤖 PERFECT FOR AI AGENTS<br>• Let your AI assistants call your phone as an LLM backend<br>• Hermes Agent, LangChain, AutoGPT — anything with HTTP<br>• Tailscale/ZeroTier support for secure remote access<br>• No API keys needed — you own the model<br><br>📱 HOW IT WORKS<br>1. Download a model from the built-in model browser<br>2. Tap &quot;Start Server&quot; to launch the API endpoint<br>3. Point any client to http://your-phone-ip:8080/v1/chat/completions<br>4. That&#39;s it — your phone is now an AI server<br><br>🔧 TECHNICAL DETAILS<br>• llama.cpp backend for fast CPU/GPU inference<br>• Supports GGUF models (Q4_K_M, Q5_K_M, Q8_0 and more)<br>• OpenAI-compatible /v1/chat/completions endpoint<br>• Configurable context length, temperature, and sampling<br>• Background service keeps serving even when app is minimized<br>• Battery-optimized inference scheduling<br><br>━━━━━━━━━━━━━━━━━━━━━━━━━━━━<br><br>💡 USE CASES<br>• Personal AI assistant that runs 100% on your device<br>• Development &amp; testing — prototype AI features without cloud costs<br>• AI agent backend — let autonomous agents use your phone as their brain<br>• Privacy-first AI — sensitive data never touches the cloud<br>• Offline AI — works on planes, in tunnels, anywhere<br><br>🔒 PRIVACY &amp; SECURITY<br>• All inference happens on-device<br>• No data collection, no telemetry, no cloud dependency<br>• API server only accessible on your local network by default<br>• Open-source model ecosystem — no vendor lock-in<br><br>━━━━━━━━━━━━━━━━━━━━━━━━━━━━<br><br>LLM Server bridges the gap between powerful open-source AI models and the devices you carry every day. Stop paying for cloud API calls — run your own AI, on your own terms.<br><br>Download now and turn your phone into an AI powerhouse.

## Rankings

- #2,891,376 — Overall

## Permissions and access

### Permissions

- `android.permission.ACCESS_NETWORK_STATE`
- `android.permission.ACCESS_WIFI_STATE`
- `android.permission.FOREGROUND_SERVICE`
- `android.permission.FOREGROUND_SERVICE_SPECIAL_USE`
- `android.permission.INTERNET`
- `android.permission.POST_NOTIFICATIONS`
- `android.permission.RECORD_AUDIO`
- `com.android.vending.CHECK_LICENSE`
- `com.llmserver.DYNAMIC_RECEIVER_NOT_EXPORTED_PERMISSION`

## Similar extensions and apps

- [Mobile LM Server - Local AI](https://chrome-stats.com/d/com.chaterminal.mobilellm) — 2,632 users, 3.80 / 5
- [LLM Hoster](https://chrome-stats.com/d/com.joblessaideveloper.llm_hoster) — 421 users
- [LLM Server - Local AI API](https://chrome-stats.com/d/uk.co.cloudspirit.gm4) — 618 users, 4.20 / 5
- [LLM AI Server with llama.cpp](https://chrome-stats.com/d/com.micklab.llama) — 8,520 users
- [TinyLLM : Offline AI](https://chrome-stats.com/d/ai.impact) — 87 users
- [AI Playground](https://chrome-stats.com/d/com.deardhruv.llmplayground) — 4,673 users, 3.50 / 5
- [LLM Hub: Offline AI Assistant](https://chrome-stats.com/d/com.llmhub.llmhub) — 48,565 users, 3.17 / 5
- [LLM Local Client](https://chrome-stats.com/d/com.ericslab.llmlocalclient) — 1 users
- [llM Local - AI offline](https://chrome-stats.com/d/llm.local) — 889 users
- [LocalAI: Offline AI Chatbot](https://chrome-stats.com/d/com.delta.local.ai.chat.agent) — 724 users
- [LLM Connect](https://chrome-stats.com/d/com.ai.llm_connect) — 7 users
- [Ollama Local AI - Chat & Build](https://chrome-stats.com/d/com.llmproxy) — 77,544 users, 4.43 / 5

---

Source: [Chrome-Stats](https://chrome-stats.com/d/com.llmserver)
