ChiChat AI vs Local Inference OnDevice Agent

ChiChat: Your All-in-One AI Assistant ChiChat brings multiple large language models, custom assistants, rich media, and voice together in one app. You can chat, create, code, and explore in a way that fits how you work. Your Models, Your Way • Custom Model Support: Connect any OpenAI-compatible LLM API, add your own endpoints and models, and switch between them anytime. • Personalized Assistants: Create assistant profiles, each with its own model, voice, system prompt, and behavior settings. • Fast, Stable Streaming: Get quick, smooth real-time responses, even for long outputs. Rich Content Preview • HTML Preview: Run AI-generated web pages, mini-games, and interactive demos right in the chat. • ECharts Visualization: Turn data into interactive charts instantly. • Mermaid Diagrams: View flowcharts, sequence diagrams, mind maps, and more. • SVG Rendering: Display vector graphics and illustrations in full detail. • Code & Source Toggle: Switch between the rendered preview and the source code with one tap. Music, Video & Images • Music Player: Play music in the chat, with synced, scrolling lyrics and background playback. • Video Playback: Watch videos inline with full-screen support. • Image Generation & Viewing: Create, preview, and zoom into images in a full-screen viewer. • Save to Photos: Download images and videos to your photo library with one tap. Voice • Multilingual Voice Playback: Hear replies read aloud by your device's built-in voice engine, with enhanced Cantonese support. • Voice Input: Speak instead of typing for faster, hands-free conversations. Productivity & Creativity • Smart Document Processing: Upload, read, and analyze complex documents. • Code Assistance: Debug, explain, and improve code. • Creative Tools: Write, brainstorm, draw, and compare ideas across models. • My Files: Manage your uploaded and generated files in one place. Polished Experience • Dark Mode & Landscape Support: Use a comfortable interface in any lighting or orientation. • Optimized Performance: Deep tuning for a smoother, more reliable app.

Your AI. Your phone. Nobody else's business. LocalInference runs powerful open AI models entirely on your device. Your conversations never leave your phone — no account, no cloud, no analytics, no tracking. Ever. PRIVATE BY ARCHITECTURE, NOT BY PROMISE • Everything runs on-device; works fully offline after a one-time model download • Zero data collection — we couldn't read your chats if we wanted to • API keys (optional) stored in the secure keychain, sent only to the provider you chose A REAL ASSISTANT, NOT JUST A CHATBOT • Tools: calculator, web search, date & time, webpage reading • Contacts & calendar integration — every write action asks you first • Ask about photos with vision models • Reads answers aloud with on-device voices BUILT FOR TINKERERS • 16 curated models from 0.5B to 8B — Qwen3, Llama, Gemma, DeepSeek R1, Phi, SmolVLM • Only models that fit your device's memory are offered • Live tok/s, time-to-first-token, and token counts per response • Thinking models show their reasoning in collapsible blocks • Bring your own keys: Anthropic, OpenAI, Google — or any OpenAI-compatible server (llama.cpp, LM Studio, Ollama) on your own network Built with Llama. Gemma models provided under the Gemma Terms of Use.