ToolsWork smarter

LM Studio

Run local language models, including DeepSeek, through a desktop chat interface.

LM Studio

A local model workspace

LM Studio lets you download models, chat with them and expose local model APIs to applications. It supports macOS, Windows and Linux.

A document task

For an illustrative task, attach a short TXT product sheet and ask which connector it specifies. Compare the answer with that file. The document guide supports TXT, PDF and DOCX: short files fitting the model context are included whole; longer files use retrieval of relevant passages, which can need tuning. Include specific source terms in your question.

Check the computer

On x64 Windows, AVX2 support is required. The Windows guidance recommends at least 16 GB RAM and 4 GB dedicated video memory; those memory figures are recommendations.

Sources(3)

OverviewChecked: 20 Oct 2026
DocumentsChecked: 20 Oct 2026
RequirementsChecked: 20 Oct 2026

Keep exploring

Explore the collection

ArticlesBuild with AI

Your first local AI trial: choose a model and check the result

Use Ollama or LM Studio for a bounded local-model trial. Separate downloaded models from cloud services, check hardware support and compare outputs against known answers.

CurioFuse

VideosBuild with AI

Ollama in an application: connect the local model

IBM Technology introduces local inference through an application example. Read the linked project prerequisites before treating the demonstration as a setup recipe.

IBM Technology3 Apr 2025

ToolsBuild with AI

Ollama

Run downloaded language models locally or select a separate cloud service. Ollama provides a terminal workflow and an API for connecting applications.

Ollama