Insight Flow vs Local LLM runner

There are insights that can only be discovered among the things you've saved. Every day you encounter countless pieces of information — but most of them slip away. Links stay in the browser, images in the gallery, notes in the notes app — and when you actually need them, they're nowhere to be found. InsightFlow brings your scattered insights together in one place, and lets AI find the connections hidden within them. ■ Effortless Saving Save links, images, and text in seconds. Use the share button from any app to save instantly. Add a note while saving so you never lose the context. ■ AI Insight Feed AI analyzes your saved content and surfaces related insights in your feed. It's not just a list — it's the experience of discovering connections between what you've collected. ■ Flow — Your Personal Knowledge Map Connect insights as nodes to build a visual knowledge structure. Add memos to connections to capture the context and relationship between two insights. As connections grow, AI synthesizes your ideas and suggests next action plans. Feel scattered thoughts come together into a single, coherent flow. ■ Reminder Insights you saved and forgot will find their way back to you. Set your preferred reminder frequency — daily, weekly, or biweekly. Experience the moment when an old insight returns with a whole new perspective. ■ Archist — Your Knowledge Journey The more you save and connect, the higher your level grows. Achievements stack up based on saves, connections, and depth of exploration — and your personal Archist rank evolves with you. Let the act of building knowledge become a journey of its own. ■ InsightFlow Pro Unlimited Flow connections, widgets, Notion/PDF export, and more. If you're ready to go deeper, try InsightFlow Pro. Value begins the moment you save. Start InsightFlow today. ——— Developer Contact: Temaworks 804, 124 Unjung-ro, Dongan-gu, Anyang-si, Gyeonggi-do, Republic of Korea alex@temaworks.com

Run LLM on your iPhone, 100% local, no network (Network needed once to download a model) Models: • Qwen2.5 0.5B Instruct — ~0.4 GB (4 GB RAM) • Llama 3.2 1B Instruct — ~0.8 GB (4 GB RAM) • Qwen2.5 1.5B Instruct — ~0.9 GB (4 GB RAM) • Llama 3.2 3B Instruct — ~1.9 GB (6 GB RAM) • Qwen3 4B Instruct 2507 — ~2.5 GB (6 GB RAM) • Qwen2.5 7B Instruct — ~4.4 GB (8 GB RAM) Also: • Add your own GGUF (for example, from Hugging Face) • Auto-estimated max context from GPU memory; you can change it Requires iOS 18 or later. Tested on iPhone 11, 14 Pro, 15 Pro with iOS 26. Qwen models © Alibaba Cloud. Licensed under Apache License 2.0. Llama 3.2 is licensed under the Llama 3.2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved. Built with Llama. On-device inference uses llama.cpp (MIT License).