Skip to main content
InferLlama
Iniciar sesión

Documentation

Everything you need to ship

Everything you need to get started with InferLlama — install the CLI, run models locally, and use the REST API.

Start here

Quickstart

Install the CLI, run your first model, and start chatting in under 5 minutes.

Read guide

CLI Reference

Full reference for every inferllama command — pull, run, serve, push, login, and more.

Read guide
OpenAI-compatible

API Reference

OpenAI-compatible REST API — endpoints, authentication, request/response schemas.

Read guide

Quick reference

inferllama runinferllama pullinferllama serveinferllama pushPOST /v1/chat/completionsGET /v1/modelsGET /v1/models/{id}GET /v1/files/{id}/download
Source code and issue tracker on GitHub →