liveBook · Manning

LM Studio

LM Studio is desktop software for downloading, configuring, running, and interacting with language models locally, including through a local server interface.

How 3 Manning books explain it

Data-Driven Cybersecurity

LM Studio is a desktop application for downloading, running, and interacting with language models through a graphical interface.

How it is used
Uses LM Studio to experiment with local language models for cybersecurity-metrics prompts, synthetic data, and risk reporting.
How deep it goes
Provides setup steps, GUI controls, and a local API example, but does not detail model internals.
Examples
Shows a Python request for a sample login-risk report and a pipeline from generated data to charts or reports.
What you can do after
Operate/configure it to query a local model and assess generated cybersecurity reports before using them.

Read how Data-Driven Cybersecurity explains LM Studio →

Domain-Specific Small Language Models

A local model-serving application and desktop environment that lets users run, chat with, and inspect models offline on their own machine.

How it is used
Runs local models for personal chat and supports developer access through a local API server.
How deep it goes
Describes model formats, chat and developer interfaces, document handling, and CLI server controls.
Examples
Uses Llama 3.2 3B Instruct, attached DOCX, PDF, and TXT files, and a local API server as examples.
What you can do after
Operate local models through chat or the CLI, or build client applications that use the REST API.

Read how Domain-Specific Small Language Models explains LM Studio →

AI Agents in Action

LM Studio is a desktop application for running large language models locally and exposing them through a server interface.

How it is used
Runs downloaded language models locally for experimentation and serves them to applications through a server interface.
How deep it goes
Walks through installation, model selection, compatibility checking, chat or server execution, and Python connection; leaves hosting comparisons to an exercise.
Examples
Uses model search and hardware checks, a locally served chat-completion request, and prompt-engineering experiments.
What you can do after
Operate/configure LM Studio to download and serve a model, then connect to it with Python and test prompts.

Read how AI Agents in Action explains LM Studio →

Related concepts

These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.