Skip to main content
Local LLM Guide

Practical local AI for real hardware

Run a local LLM on your computer.

Find a language model that fits your hardware, choose an app such as Ollama or LM Studio, and follow a setup guide for Mac, Windows, or Linux. Start by checking your computer below.

Check my setupLearn how memory fit works

Example result

16GB Apple Silicon Mac

Start with a 7B–8B model in a common 4-bit build. Use LM Studio for the easiest graphical setup, or Ollama when you want other apps to use your model. Use macOS 14 or newer and start with short conversations.

Model size
7B–8B, 4-bit
First app
LM Studio
Bottleneck
Memory shared with macOS and apps
Compare LM Studio and Ollama →

Hardware Fit Lab

Find a sensible first setup.

Choose your computer and what you want to do. Get an app and a starting model to investigate for chat, coding, or documents. These are example settings until you enter your answers.

Computer
System memory (RAM)
Mac chip or graphics
Goal

Memory amounts are used as GiB in this estimate: 1 GiB is about 1.07 GB. RAM and dedicated graphics memory remain separate.

Your first local model

What is a local LLM?

A local LLM is a large language model that runs on your computer to answer questions, draft text, or help with code. You download the model and use an app to run it. Cloud models and connected tools can still send data elsewhere.

Read the beginner’s guide to local LLMs →

Check local LLM hardware requirements

Understand RAM, GPU memory, and how model size changes what fits.

Set up a local LLM with LM Studio

Use a desktop app to download a model, load it, and start a chat.

Set up a local LLM with Ollama

Follow the Mac, Windows, or Linux installation steps and run your first model.

Start with the job

What would you like to do?

Choose a task below, or browse the model and app lists to compare more options.

I want the simplest first setup

Install one desktop app, choose one sensible model, and get a successful first response before touching advanced settings.

Use the graphical setup path

I want to chat with documents

Choose an app, add a short PDF, and check that its answers match the document.

Build a document workflow

I need the right model for my machine

Find a model that fits your computer and works in your chosen app.

See the curated model shortlist

Something is broken

Start with the symptom: a model will not load, generation is slow, the GPU is missing, apps cannot connect, or document answers are bad.

Diagnose the failure

Common decisions

The questions that usually decide the setup.

8GB, 16GB, or 32GB?

See what each memory tier changes.

Ollama or LM Studio?

Choose typed commands or a desktop app with menus.

Is the workflow actually local?

Check where your prompts and documents go.

Want to compare more options?

Browse model details and compare their sizes, supported apps, and hardware needs.

Explore models