OnDevice Models - AI Gallery

AI Gallery runs large language models directly on your phone—so your chats and photo questions stay on your device, not in the cloud.

PRIVATE, OFFLINE AI
• No sign-in required to start chatting
• Inference runs locally after you download a model
• Use on planes, poor networks, or anywhere you want more privacy
• Your prompts and images are not sent to our servers for AI processing

CHAT WITH OPEN MODELS
• Built-in model library with size guidance for your device
• Pick lightweight models for everyday questions or larger models when you have more RAM
• Supports popular on-device families including Qwen and Gemma
• Streaming replies for a natural chat experience

VISION & MULTIMODAL
• Ask questions about photos you choose from your library
• Multimodal models for image understanding on supported devices
• Great for quick captions, explanations, and visual Q&A—without uploading pictures to the web

BUILT FOR REAL PHONES
• Recommendations based on available device memory
• Download only the models you want
• Optimized native runtimes on android (LiteRT-LM, and llama.cpp where supported)

WHO IT’S FOR
• Students, travelers, and professionals who want offline AI
• Privacy-conscious users who prefer on-device assistants
• Developers and enthusiasts exploring local LLMs on android

HOW IT WORKS
1. Open the model library and download a model (one-time, over Wi‑Fi recommended).
2. Start a chat—or attach an image with a vision-capable model.
3. Chat offline anytime after the model is installed.

IMPORTANT NOTES
• Model files are large; downloads use storage and are best on Wi‑Fi.
• Performance depends on your phone model and free RAM; heavier models need newer, higher-memory devices.
• AI Gallery is a client for on-device open models; it is not affiliated with Google, Alibaba, or other model publishers.

Questions or feedback? Contact us at contact@appaxis.ca