Pintaz Scan vs Local Inference OnDevice Agent

Pintaz Scan turns your iPhone's LiDAR into a complete site-survey tool. Walk through a room once and get a measured floor plan plus a Real 3D textured model — all processed on your device, all free. BUILT FOR SITE VISITS Made by a former architect for architects, interior designers, renovators, and property agents. Scan the space during your site visit and leave with the floor plan and 3D model already done. SCAN A ROOM • Walk the room — walls, doors, windows and furniture are detected automatically • Color Capture: a quick sweep paints the room orange as it captures real textures • Get a 2D floor plan with measurements and a Real 3D textured model SCAN AN OBJECT • Capture furniture and objects as textured 3D models • On-device photogrammetry — no cloud, no upload EXPORT ANYWHERE • Floor plan as PDF or DXF (AutoCAD, SketchUp, ArchiCAD) • 3D models as GLB or USDZ (Blender, AR Quick Look) FREE AND PRIVATE • No account, no subscription, no watermarks • Everything is processed and stored on your iPhone — nothing is ever uploaded Requires an iPhone Pro with LiDAR (iPhone 12 Pro or newer Pro models).

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.