Local LLM runner vs Bloks

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).

Bloks turns AI agents into little colleagues that live on your Mac. This is their phone app. Pair it with Bloks on your Mac by reading a six digit code off its screen. From then on, your agents are in your pocket: see what each one is working on, answer the question that is blocking one, approve or refuse the thing it wants to do, and watch a room of them work through a plan together. Answers arrive as the thing itself rather than a wall of text: a chart, a checklist, a decision with its options laid out. When an agent needs you, your phone buzzes, and the answer is one tap away. Your agents run on your Mac, with your own provider keys. The phone talks to your Mac directly, there is no account to create, and there are no analytics and no tracking in this app. New here? The app opens with a sample workspace so you can feel how it works before connecting your own. Bloks for Mac is free and open source: github.com/hamedgitty/bloks