OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Local & Self-hosted AI

LLM Hub

LLM Hub is an open-source Android and iOS app for on-device language-model chat, image generation, video generation and music generation. It supports multiple model formats and mobile CPU, GPU and NPU acceleration, with additional tools for transcription, translation, speech and agent-assisted tasks.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

LLM Hub — OpenViST project profile in Local & Self-hosted AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use LLM Hub when you want mobile access to on-device model chat or generative media, or when a documented platform-specific tool such as Android Termux command drafting or iOS video generation matches your task.

Who it is for

  • People who want to chat with language models on a mobile device.
  • Mobile creators looking for on-device image, video or music generation.
  • Android users who want an AI assistant that can draft Termux commands for review and execution.
  • Users seeking local tools for speech transcription, translation or media search.

Documented uses

  • Run multi-turn conversations with local language models.
  • Generate images, video or music using the platform-specific tools described in the project documentation.
  • Transcribe speech with on-device Whisper models or translate text, images and audio offline.
  • Search photos and videos by description or reference image, or find a described moment in a video.
  • Use an Android agent to prepare Termux commands and review them before execution.
Before you choose

Requirements & limits

The project README links to Google Play and the Apple App Store. Native Windows and macOS apps are described as planned.

  • Features differ by platform: video generation is listed for iOS; Termux command generation and SoundGen are listed for Android.
  • The README describes CPU, GPU and NPU acceleration and support for multiple model formats; it does not specify device-level requirements in the supplied material.
  • MCP tool calls require user approval, and Android shell commands can be inspected and edited before execution.
  • Some models may require license acceptance to download in local development builds.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Build and run LLM Hub on an iPhone with Xcode

Build the iOS project and run it on an iPhone for local testing.

Before you start

  • A Mac with Xcode installed; the Xcode version should match the iOS device version.
  • An Apple ID signed into Xcode; a free Personal Team is sufficient for local device testing.
  • An iPhone with Developer Mode enabled when using real hardware.

Steps

  1. Clone the repository, change to its directory, and open ios/LLMHub/LLMHub.xcodeproj.

  2. In Xcode, select the LLMHub target and open Signing & Capabilities. Set your Team and a unique Bundle Identifier, leaving Automatically manage signing enabled.

  3. Select the iPhone as the run destination and press Run.

Expected outcome

The project is built and launched on the selected iPhone for local testing.

Guide limitations

  • The listed prerequisites and steps cover iOS development on macOS with Xcode; they do not describe Android setup.
  • The source describes local device testing, not production distribution.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗Guide documentation ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
timmyy123/LLM-Hub · Official homepage title · retained in its source language
How we review sourcesSuggest a correction