Notes from the studio.
News, guides and engineering notes on running AI locally.
How to Run Qwen 3.8 27B on Your Own Computer
The open weights landed on 13 August. Here is what the 27B model needs in disk and memory, why its context window is cheaper than it looks, and the one setting that decides whether it works at all.
Kimi K3 and Ling 3.0 Flash Are Live in LU Labs Cloud, on Every Plan
The first open 3T-class model and the most efficient 124B MoE just landed in the catalog. What each one is for, what it costs in credits, and how the thinking toggle keeps K3 affordable.
Kimi K2.6 in LU Labs Cloud: The Agent Workhorse, and How to Get the Most From It
Kimi K2.6 is one of the best open models for coding agents and long documents, and it's live in LU Labs Cloud. What it's good at, where it isn't, and how to use it well.
Kimi K3 Is Here: What Moonshot's 2.8T Model Means for Your Studio
Kimi K3 launched with 2.8 trillion parameters and a 1M token context. What's real, what's claimed, when it can land in LU Labs Cloud, and why Kimi K2.6 is already the smart pick today.
Generate AI Images on Your Own Computer: Free, Offline, Yours
How to generate AI images on your own computer: free, offline and unlimited. The hardware you need, the models worth trying, and how to get started.
How Much RAM Do You Need for Local AI?
Practical RAM guidelines for local AI in 2026: what runs on 8, 16, 32 and 64 GB, how quantization shrinks models, and how to pick a model that fits.
How to Run AI Models Locally on Your Mac (2026 Guide)
Step-by-step 2026 guide to running AI models locally on your Mac: which Macs can handle it, how model sizes work, and the easiest apps to get started.
Introducing LU Labs: A Free Desktop Studio for Local AI
LU Labs is a free desktop app that turns your Mac or PC into a private AI studio: chat, coding agents, image and video generation, all running locally.
Local AI Video Generation in 2026: What Actually Works
An honest look at local AI video generation in 2026: which open models really run on home hardware, what the clips look like, and how to try it yourself.
Local AI vs. Cloud AI: What Actually Stays Private?
A plain-English comparison of what cloud AI services can see and keep versus what stays on your machine with local AI, and how to choose between them.
Ollama vs. LM Studio vs. LU Labs: Which Local AI Setup Fits You?
Ollama, LM Studio and LU Labs compared: strengths, ideal users, and how they actually fit together, so you can pick the right local AI setup for you.
The Best Open-Weight LLMs You Can Run at Home in 2026
A consumer-friendly tour of the best open-weight LLMs in 2026 (Llama, Qwen, Mistral, Gemma, DeepSeek distills and Phi) and which fit your computer.
What Is an AI Agent, and Why Run One Locally?
What an AI agent actually is, how it differs from a chatbot, and why running one locally keeps your files and code private. Plus how to try one for free.