Local AI: Offline Chat & Image

🚀 Run AI Entirely Offline & Private on Your Device

Stop sending your data to the cloud. Local AI lets you run powerful Large Language Models (LLMs) and Stable Diffusion image generators directly on your phone. No internet? No problem. Total privacy is guaranteed because everything processes locally.

🤖 AI Chatbot (Local LLM)
Powered by Llamatik for fast on-device inference.

Download & Chat: Choose from 20+ optimized models (from 1B to 22B parameters).

Privacy First: Your conversations never leave your device.

Multilingual Support: Models supporting English, Chinese, Spanish, French, German, Japanese, Korean, and more.

Customizable: Adjust Max Tokens and Temperature for creative or precise responses.

Categories: Ultra-Light (1B), Mid-Size (3B-9B), Large Context (128K+), Math & Reasoning, Roleplay, and Coding models.

🎨 AI Image Generator (Stable Diffusion)
Create stunning art offline using SD1.5 based models.

CPU & NPU Support: Optimized for general devices and accelerated for Qualcomm Snapdragon (8 Gen 1/2/3/Elite).

Advanced Modes: Supports Text-to-Image, Image-to-Image (img2img), and Inpainting.

Custom Models: Import your own .safetensors files and LoRAs.

Control: Adjust Steps, CFG Scale, Schedulers, and Seeds.

📹 AI Video Generator

Coming Soon: On-device text-to-video generation. (Placeholder for future update).

🛠️ Key Features You'll Love

File Manager: Manage downloaded model files and embeddings.

Embedding Manager: Import .safetensors embeddings for style control.

High-Res Upscaler: Enhance images using dedicated AI upscaling models.

Modern UI: Clean Material Design with dynamic theming and bottom navigation.

Background Downloads: Download large models while using other apps.

📱 Device Requirements

Storage: 2GB - 15GB free space depending on models downloaded.

NPU Acceleration: Requires Qualcomm Snapdragon 8 Gen 1 or newer (falls back to CPU/GPU automatically).

Permissions: Storage (to save images) and Notifications (for background tasks).

⚠️ Note
First-time generation may be slower while caches are built. Larger models require more RAM and storage.

Download Local AI today and experience the future of on-device artificial intelligence!