◂ Back to Profiq blog

profiq Video: How to Download and Run a Local LLM with LM Studio by Miloš Švaňa

Run local LLM using LM Studio

In recent years, large language models (LLMs) have revolutionized the way we interact with technology. From enhancing productivity to enabling creative applications, their potential is vast. How challenging is it to run a powerful LLM directly on your PC or laptop? LM Studio is a user-friendly app that allows you to easily manage and run LLMs on your computer. It offers a streamlined interface, making it accessible even for those new to machine learning.

In this video tutorial, Miloš Švaňa walks users through how to choose, download, and run an LLM locally using LM Studio. Miloš is a PhD in Systems Engineering, ML engineer, and a profiq researcher who specializes in large language models, deep learning, classical ML, and statistics.

Miloš begins by showing users how to download and install LLM studio, demonstrates how to find and set up your LLM, and finally, how to start a new project and start chatting. Follow along in the video and/or the step-by-step instructions below.

Important Timestamps In The Video
0:00-0:14: Intro
0:14 Downloading LM Studio from lmstudio.ai
0:34 Finding the appropriate LLM model to download and run
1:02 Chatting in the chat section of the chosen model
1:10 Changing GPU offloading
1:20: Offloading layers to generate text more quickly

Step 1: Download and Install the LM Studio
1. Visit the Official Website
2. Select Your Operating System: Choose the version that matches your PC or laptop’s operating system (Windows, macOS, or Linux).
3. Download and run the installer
4. Follow the instructions and complete the Installation: Once installed, launch LM Studio from your applications folder or desktop shortcut

Step 2: Find Your LLM Within LM Studio, you can easily browse through available models. Look for the “Model Library” to explore options. Each model typically comes with a description, highlighting its strengths and potential use cases. Step 3: Download and Load the Model

  1. Select a model and download: Once you’ve selected your model, hit the “Download” button. Depending on the model’s size, this may take a few minutes.
  2. Open and load the Model: Navigate to the “My Models” section to find your downloaded model. Click “Load” to initialize it within LM Studio.

Step 4: Run Your LLM

  1. Create a New Project: From the main menu, select “New Project” to get started.
  2. Choose Your Model: In the project settings, select the LLM you’ve just downloaded.
  3. Input Data: You can now input your text in the designated area. Whether you want to generate text, summarize, or analyze, just type it in.
  4. Adjust Your Settings: Depending on the task, you can tweak various parameters, like temperature and max tokens, to refine the model’s output.
  5. Run the Model: Click the “Run” button and watch as your LLM processes the input and generates the desired output.

Conclusion Running a local LLM on your PC or laptop has never been easier, thanks to the LM Studio app. By following these straightforward steps—choosing the right model, downloading LM Studio, setting up your LLM, and running it—you can unlock the power of AI right from your desktop. Whether you’re looking to enhance your productivity or embark on creative projects, the possibilities are endless. Happy experimenting! You May Also Like:
profiq Video: Tech demo – Autonomous Agents using LLMs by Viktor Nawrath
profiq Video: Training your own speech-to-speech AI model
profiq blog: Let’s make LLMs generate JSON!
profiq blog: Notiondipity: What I learned about browser extension development
LM Studio Official Website
InfoWorld: 5 easy ways to run an LLM locally

Anke Corbin

Written by

Anke Corbin

Comments

Leave a Reply

Online comments are not active during the static migration phase.
AI Function Blog Image

Is The Most Valuable AI Function Asking Better Questions?

How the "Grill Me" method became a key part of Project Weaver's approach to AI-assisted software development. We've shared some of the thinking behind Project Weaver—the internal engineering framework we've developed at profiq to help our teams and AI work together more effectively. Rather than treating AI as a magic code generator, Weaver is built around a simple idea: the better the structure, context, and engineering discipline, the better the outcomes.

Posted 3 weeks ago by Anke Corbin

Weaver Prototype Image

From Vibe-Coded Prototype to Production-Ready App Using Weaver

There's an important distinction between a prototype that demonstrates an idea and a system that can support a real business. Recently, we had the opportunity to explore that distinction firsthand while working with Ginger & Nash on an application called c.h.i.p. using profiq Weaver as an AI assistant.

Posted 4 weeks ago by Anke Corbin

Project Weaver Recap

Quick Recap: Project Weaver Engineering Series

We wanted to do another quick recap of the Weaver journey so far for those of you who are just learning about the project, from the first idea through the latest automation and workflow experiments.

Posted 1 month ago by Anke Corbin

Read the Blog