TopicFlow vs Local LLM runner

TopicFlow turns AI chats into reusable notes, plans, outlines, decisions, and summaries. Instead of leaving every AI conversation as one long thread, TopicFlow gives your thinking structure. Keep your main line clear, branch into focused follow-up chats, then bring the strongest results back into reusable work. What you can do with TopicFlow: - Capture ideas before they disappear from long chat threads. - Branch AI chats for questions, alternatives, research notes, and next steps. - Refocus a conversation without rewriting prompts from scratch. - Turn selected discussion into notes, plans, requirements, decision records, or summaries. - Organize topic history locally on your device. - Use TopicFlow subscription access for DeepSeek-powered AI inside the app. - Export and share only when you choose. - Back up to your own iCloud or Google Drive app data space when backup is enabled. TopicFlow is built for writers, founders, builders, students, and independent thinkers who want AI conversations to produce durable work instead of disposable chat history. Important: TopicFlow subscription access unlocks the app workflow and hosted DeepSeek-powered AI features. AI availability, quotas, fees, rate limits, output rules, and terms may still be governed by DeepSeek and app store purchase rules. Terms of Use (EULA): https://specaxe.com/terms

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).