CruxAI vs Local LLM runner

CruxAI is a fast, modern AI assistant designed to make conversations, research, and creativity more seamless. CruxAI combines powerful AI capabilities with a clean, responsive and familiar interface. Chat naturally with AI through text or Live Mode (voice conversations). Generate images, search conversations instantly, and explore information with deep search tools designed to help you find exactly what you need. CruxAI also introduces an extensible “Specialists” system that allows custom AI experiences built by other users. Create your own tools, publish them for others, or explore specialists created by the community. Key Features: • Real-time voice conversations with Live Mode that includes music recognition • Fast, high quality image generation • Deep message search across conversations • Community-driven AI Specialties and custom assistants or skills • Clean interface designed for productivity and exploration • Privacy focused and tons of personalization and customization options • Integration with Crux Cloud • Locally run models on supported devices • Sandbox to create files and projects on the go • Personal Context with other Crux Interactive services • Record Voice & Meeting notes to get summaries and more CruxAI focuses on speed, flexibility, and extensibility, giving you a powerful AI platform that adapts to how you work and think. EULA: https://www.apple.com/legal/internet-services/itunes/dev/stdeula/

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).