AI that works
in airplane mode.
15+ AI models running 100% on your phone. Chat, images, video, music, code — with zero signal, zero accounts, zero tracking.



New: LLM Hub for desktop
Now on your computer, too.
Native apps for Mac, Windows and Linux. The same private AI, with room for bigger models, agents and creative work.
Windows
Windows 10 (2004) or later
The Windows installers are new, so SmartScreen may ask first. Choose More info, then Run anyway.
Version 0.1.3All files and checksums
Chat
Local models with web search, attachments and voice dictation.
Agent
Claude Code and OpenClaw, powered by the models on your computer.
Design
Turn a prompt into slides and web pages, then export them.
Studio
Create images, video and music, and search your own photos, audio and videos.
Local API
OpenAI and Anthropic compatible endpoints for your other apps.
Image Generator
Generate Stunning Images, Fully On-Device
Experience the magic of Stable Diffusion running entirely offline on your phone. Powered by native NPU and GPU compilers for lightning-fast edge inference.
100% Private Offline Generation
Prompts, seeds, and generated images stay strictly on your local device storage. Zero external server requests.
Qualcomm NPU / GPU Accelerated
Optimized for mobile accelerators (CPU/GPU/NPU) utilizing high-speed MNN and QNN backends for Snapdragon chips.
Absolute Reality SD1.5 Checkpoint
Generates beautiful, photorealistic, and highly detailed art offline with high-fidelity, resource-efficient weights.
Vibes Coder
Design Apps and Sites, Preview in Real-Time
A full-featured mobile coding environment powered by local models. Write natural language descriptions and see dynamic, functional web views render before your eyes—no cloud server needed.
Instant HTML/JS/CSS Previews
Write prompts, generate full front-end code, and run it in a secure local sandbox with real-time browser previewing.
100% On-Device Code Models
Harness local coding intelligence powered by state-of-the-art quantized model weights running natively on your hardware.
Pure Local Playground
Zero external dependencies, zero cellular data consumed, and absolute privacy. Code and execute with 100% offline security.
AI Agent
Run Termux Commands, Control Apps & Maps
An autonomous on-device AI agent for Android & iOS. Generate and execute shell commands inside Termux, render location maps, compose messages, and update calendar schedules—100% offline.
Termux Command Execution
Generate CLI scripts and execute shell commands directly inside the app terminal environment.
Interactive Location & Maps
Search locations, view coordinates, and render interactive map views dynamically on demand.
Messaging & SMS Automation
Compose and dispatch text messages and notifications autonomously through local Android APIs.
Music Generator
Generate Music On-Device, Fully Offline
Run Google Magenta Realtime 2 on iOS or Stable Audio Small on Android and generate music on device.
Google Magenta Realtime 2 (iOS)
Generate expressive real-time audio and musical compositions directly on Apple silicon.
Stable Audio Small (Android)
Ultra-fast sound synthesis and high-quality audio generation optimized for mobile devices.
100% On-Device & Private
All music synthesis runs offline. Zero server requests, total privacy for your creative audio.
Every tool runs on your phone.
Every feature runs 100% on your device. Your data never leaves your phone.
AI Chat
Multi-turn conversations with 15+ AI models. RAG memory, web search, and TTS auto-readout.
Image Generator
Generate images from text prompts with Stable Diffusion — GPU/NPU accelerated.
Video Generator
Create AI videos from text and image prompts on-device — fully offline.
Music Generator
Real-time music generation on-device: Google Magenta Realtime 2 on iOS, Stable Audio Small on Android.
Vibes Coder
Full on-device coding environment. Write a prompt, preview running HTML/JS/CSS instantly in a sandbox.
AI Agent
Autonomous on-device agent to run Termux shell commands, render interactive maps, send messages, and manage calendar events.
VibeVoice
Hands-free AI voice chat with natural conversations, powered by Whisper ASR and Kokoro TTS for real-time voice input/output.
Translator
Translate text, images (OCR), and audio across 50+ languages. Works fully offline.
Transcriber
Convert voice or audio to text offline using Whisper ASR and Gemma models.
Writing Aid
Grammar, style, paraphrasing, tone adjustment, and code generation — all on-device.
Image Upscaler
Upscale and enhance images on-device — fully offline.
Media Search
Search your gallery's photos and videos by meaning with on-device EmbeddingGemma 2 — fully offline.
Video Moments
Find the exact moment inside any video with on-device EmbeddingGemma 2 semantic search.
Voice Clone
Clone a voice on-device with the Pocket TTS model and generate natural speech — fully offline.
Scam Detector
Analyze text, images, or URLs for potential scams with AI risk assessment.
creAItors
Create powerful custom AI personas — from pirate narrators to full-stack system architects.
- 100% Private
- No Internet Required
- Zero Data Collection
- Open Source
- GPU/NPU Accelerated
A closer look at the app.
Screens from LLM Hub on iPhone, as shown on the App Store.
Download once. Run forever.
15+ models, quantized for your pocket. Pick your weights, keep them on-device.
Gemma-3 1B
Google
Optimized text models for mobile with GPU acceleration. Multiple quantizations and context windows (1.2k-4k)
Google
INT4 - 529MB · INT8 - 1005MB-1024MB
TextGemma-3 GGUF Multimodal
Google
GGUF multimodal models with vision projectors for CPU/GPU/NPU acceleration
Google
4B (3.0GB) · 12B (7.7GB)
VisionGemma-3n Multimodal
Google
Multimodal models with text, vision, and audio capabilities. Selective parameter activation
Google
E2B (3.15GB) · E4B (4.33GB)
VisionLlama-3.2 (LiteRT)
Meta
Meta's INT8 models for on-device inference with 4k context
Meta
1B (2.01GB) · 3B (5.11GB)
TextLlama-3.2 GGUF
Meta
GGUF format Llama models with 128k context and CPU/GPU/NPU support
Meta
1B & 3B - Multiple quantizations
TextIBM Granite 4.0 H-Tiny
IBM
Compact enterprise model with 128k context window and multiple quantizations
IBM
7B - Q2_K to f16 (2.59GB-13.9GB)
TextIBM Granite 4.0 H-Small
IBM
High-quality enterprise model with 128k context window
IBM
32B - Q2_K to f16 (11.8GB-64.4GB)
TextPhi-4 Mini
Microsoft
Microsoft's efficient model for advanced reasoning with GPU support on 8GB+ devices
Microsoft
INT8 (3.91GB)
TextLFM-2.5 1.2B Instruct
LiquidAI
LiquidAI's efficient instruction model with 128k context. Available in GGUF and ONNX formats
LiquidAI
GGUF & ONNX variants
TextLFM-2.5 1.2B Thinking
LiquidAI
Reasoning model with 'thinking' mode support and 128k context. Available in GGUF and ONNX
LiquidAI
GGUF & ONNX variants
TextLFM-2.5 VL 1.6B
LiquidAI
Vision-language model supporting both text and image input with 128k context
LiquidAI
GGUF with vision projectors
VisionMinistral-3 3B
MistralAI
Multimodal instruction model with vision support and 262k context. Available in GGUF and ONNX
MistralAI
GGUF & ONNX variants
VisionGemma 4
Google
Multimodal model with text, vision, and audio capabilities for on-device chat and reasoning. Multiple quantizations
Google
Multiple quantizations
VisionMuse Glimmer
Meta
Multimodal model for on-device chat. Multiple quantizations
Meta
Multiple quantizations
VisionGranite 4.1
IBM
Enterprise text model with long context window. Multiple quantizations
IBM
Multiple quantizations
TextGranite 4.2
IBM
Enterprise text model with long context window. Multiple quantizations
IBM
Multiple quantizations
TextAbsolute Reality SD1.5
Stable Diffusion
Image generation model for creating images from text prompts
Stable Diffusion
MNN (CPU) · QNN (NPU)
ImageSDXL
Stable Diffusion
High-quality image generation model for creating images from text prompts
Stable Diffusion
MNN (CPU) · QNN (NPU)
ImageGecko-110M
Google
Compact embedding model for RAG memory system with multiple dimension options
Google
64D-1024D embeddings
RagEmbeddingGemma-300M
Google
High-quality text embeddings for enhanced RAG retrieval and semantic gallery/video search
Google
High-quality embeddings
RagWhisper ASR
OpenAI
State-of-the-art automatic speech recognition (ASR) model for converting voice/audio to text offline
OpenAI
Highly lightweight quantizations
TextKokoro TTS
Kokoro
State-of-the-art text-to-speech (TTS) model for producing highly natural voice synthesis on-device
Kokoro
Extremely lightweight & efficient
TextSupertonic 3
Supertonic
Text-to-speech (TTS) model for natural voice synthesis on-device
Supertonic
Extremely lightweight & efficient
Text
Private AI in three steps.
Grab the weights once. Everything after that happens on your hardware.
Install LLM Hub
Free to download on the App Store and Google Play, or build it from source on GitHub.
Download a model once
Choose from 15+ models. They're saved on your device, not in the cloud.
Use it anywhere
Chat, create and translate offline, even in airplane mode.
Frequently Asked Questions
Everything you need to know about LLM Hub, running 100% privately on-device.
Yes, LLM Hub is completely open-source. Download it from Google Play, the Apple App Store, or build it directly from source on GitHub.








