LMQL

Key Features

What the engine gives you out of the box, in plain language.

• OpenAI-Compatible API
• NVIDIA GPU
• AMD GPU
• Apple Silicon
• CPU Inference
• Quantization
• Continuous Batching
• Multi-GPU
• Desktop GUI
• One-Line Install
• Structured Output
• Streaming

• Prompt query language

  Write prompts with variables, constraints, and logic in one place.

• Built-in constraints

  Limit output length, set choices, and enforce conditions during generation.

• Multiple backends

  Run queries against local models or hosted APIs.

Where It Shines

The jobs this engine is best suited for.

• Constrained generation

  Keep output within strict bounds using prompt-level rules.

• Multi-step prompting

  Express branching prompt logic without scattering it across code.

• Research and teaching

  Explore how constraints shape model behaviour.

Frequently Asked Questions