Forgeworker guide

vLLM

High-throughput open-source model serving. An open-source inference and serving engine for supported language models and OpenAI-compatible APIs.

About vLLM

An open-source inference and serving engine for supported language models and OpenAI-compatible APIs.

How you access it

Run locally or self-host it. Open source, Self-hosted

Capabilities

  • Model serving
  • OpenAI-compatible API
  • Batching

Published pricing

Open source; infrastructure costs apply

Review note

Directory reviewed on 2026-07-28. Review the provider privacy policy before sending sensitive information.

ComfyUI

Build visual generative-media workflows locally.

Ollama

Run supported language models on your own machine.

LM Studio

Discover and run local models from a desktop app.

LangChain

Frameworks and tooling for agentic applications.

This server-rendered summary is available to search engines and no-JavaScript visitors. JavaScript loads the full interactive experience.