Literal Labs’ logic-based models are the fastest way to run AI

Run low-power, AI models up to 250× faster. And do so on-server or on-device and on the edge. Enable new business cases and deployments across a whole range of problem domains.

Our models’ performance

Anomaly detection benchmarks

54x

faster

52x

less energy

Inference per second

Energy use

Literal Labs model

Published optimised model

A new logic for AI
A new standard for performance

By building our AI models on a foundation of logic, we’re able to unlock the four key advantages that set logic-based AI apart: ultra-low power use, lightning-fast inference, tiny model size, and explainable AI. These are the metrics that matter most for today’s critical systems—and we’re building for each of them.

More speed

54× faster inferencing than neural networks with logic-based AI models

More energy efficient

Logic-based algorithms can achieve 52× lower energy usage than neural networks

More explainable

Logic-based AI is naturally explainable, ensuring accountability for decisions made by the model

More cost-efficient

Reduce system costs by lowering compute complexity, inference costs, and bill of materials

A logical approach

While capable of handling complex machine learning tasks like neural networks, Literal Labs’ logical approach to AI algorithms offer a refreshing alternative—one that’s faster, more energy‐efficient, and naturally explainable.

Unlike neural networks, which are inspired by biology, our logic-based AI is rooted in propositional logic. This makes it far more efficient, streamlining inference and reducing computational complexity, all while consuming significantly less energy.