Local AI. Private. Powerful.

Your Private LLM
Workspace

Chat with local models, multiple providers, and keep your data on your device. Experience the future of personal AI.

Download APK

See It In Action

Beautiful, intuitive interface across Android, Tablet, and Web

Chat Interface

Android Screenshot

Android

Chat Interface

Clean, intuitive chat UI with markdown rendering, code highlighting, and thinking mode visualization

Model Selection

Tablet Screenshot

Tablet

Model Selection

Switch between providers and models seamlessly mid-conversation

Local Models

Android Screenshot

Android

Local Models

Download and manage on-device AI models with progress tracking

RAG Documents

Web Screenshot

Web

RAG Documents

Add PDFs and documents for context-aware AI responses

Provider Settings

Tablet Screenshot

Tablet

Provider Settings

Configure multiple LLM providers with API keys and custom settings

Personas

Web Screenshot

Web

Personas

Create custom AI personalities with system prompts

Powerful Features

Everything you need for a premium AI chat experience, running locally or in the cloud.

Local AI Models

Run AI models directly on your device with ExecuTorch (.pte) and Llama.cpp (.gguf) support. No internet required.

Multi-Provider Support

Connect to OpenAI, Anthropic, Ollama, or any OpenAI-compatible API. Switch providers seamlessly mid-conversation.

RAG Integration

Add document sources to your conversations. PDFs and text files are automatically embedded for context-aware responses.

Personas

Create custom AI personalities with system prompts. Switch between personas for different use cases.

Model Management

Download models from HuggingFace or import local files. Track progress, manage storage, and configure each model.

Cross-Platform

Native apps for Android and iOS with full local model support. Web version for remote providers.

Local First Storage

All conversations and settings stored on your device. Export and import your data anytime.

Privacy Focused

No tracking, no ads, no data collection. Your conversations stay yours. Open source and transparent.

Built With Modern Tech

Powered by cutting-edge technologies for performance, privacy, and developer experience.

React Native

Cross-platform mobile development

Expo

Universal React applications

ExecuTorch

On-device AI by Meta

Llama.cpp

GGUF model inference

WatermelonDB

High-performance local database

Zustand

State management

AI SDK

Vercel AI SDK for providers

TypeScript

Type-safe development

Your AI, Your Rules

ModelFlux is an open-source project built with one goal: giving you complete control over your AI interactions.

Whether you prefer running models locally on your device for maximum privacy, or connecting to cloud providers for cutting-edge capabilities, ModelFlux provides a unified interface that works everywhere.

No tracking. No data collection. No compromises. Your conversations stay on your device, and your data is always under your control.

100%
Open Source
6+
LLM Providers
30+
Downloadable Models
3
Platforms

App Screenshot

Android or Web UI preview

Frequently Asked Questions

Everything you need to know about ModelFlux

ModelFlux is an open-source, cross-platform AI chat application that lets you interact with various Large Language Models. You can use cloud providers like OpenAI and Anthropic, connect to local servers like Ollama, or run models directly on your device using ExecuTorch or Llama.cpp.

Yes, ModelFlux is completely free and open source. You only pay for the API usage if you use cloud providers like OpenAI or Anthropic directly. Local models and Ollama are completely free.

Absolutely! On Android devices, you can download and run local models using ExecuTorch (.pte) or Llama.cpp (.gguf). Once downloaded, these models work completely offline with no internet required.

ModelFlux supports Android, and Web platforms. The native Android app has full support including local on-device models. The Web version supports remote providers (OpenAI, Anthropic, Ollama). iOS support is coming soon.

Yes! All your conversations and settings are stored locally on your device. We don't collect any analytics or usage data. When using cloud providers, your data goes directly to their APIs - we never store or intercept it.

RAG (Retrieval-Augmented Generation) lets you add documents (PDFs, text files) to your conversations. The app extracts and embeds the content, then uses it to provide context-aware responses. This works with both local and cloud models.

Personas are custom AI personalities you can create with system prompts. Based on the Character Card V2 specification, they let you customize how the AI responds - from helpful assistants to specialized experts or creative characters.

Go to Settings > LLM Providers > Add Provider. Choose from OpenAI, Anthropic, Ollama, or OpenAI-Compatible (for services like LM Studio, Together AI, etc.). Enter your API key and base URL as needed.

Yes! You can change the LLM provider or model at any point during a conversation. Previous messages are preserved, and future responses will use the newly selected model.

Go to Settings > Data Management > Export Data. Your conversations, personas, and settings will be exported as a JSON file that you can import later or use as a backup.