Running AI models on your own device starts with one important question: What can your hardware actually handle? This guide explores simple ways to check your device capabilities, understand which models are a good fit and get started with local AI without sacrificing performance. Have you tried running an AI model locally? What device are you using? 👇

Quick clarification because I see this mixed up constantly, including in vendor marketing. DeepSeek, Qwen, Gemma, and Llama are all called "open source" regularly. None of them are. They're open weight, and that's a different thing. Open weight: trained parameters are downloadable, you can run the model on your own infrastructure and fine-tune it. Training code and training data are usually not included. Open source (strict definition, per the Open Source Initiative): weights + full training code + enough documentation on the training data that you could actually rebuild and audit the system from scratch, under a license with no usage restrictions. Very few models clear this bar. Closed model: no weights, no code, access only through an API. Claude, GPT, Gemini. Why it matters if you're building with these models: License terms vary a lot within "open weight." Llama's Community License requires permission above 700M monthly active users, and Meta can refuse it. DeepSeek's recent releases ship under MIT, no such restriction. Reproducibility is different too. Open weight lets you run the model. Open source lets you rebuild it. That distinction matters if you're doing anything where audit or reproducibility is a requirement, not just a nice-to-have. Before picking a model for a production workflow, check the license directly rather than going by the label on the model card. Three questions: are the weights actually available, is the training code available, what does the license permit you to do with it.