Architecture

Sparse Model

Definition

A model architecture that activates only a subset of its parameters for any given input, rather than the full network. Sparse models—enabled by Mixture of Experts designs—achieve larger total capacity while keeping per-inference compute manageable.

Related Terms

Mixture of Experts (MoE)

A model architecture where different sub-networks ("experts") specialise in different types of inputs, and a gating network routes each token to the most relevant experts. MoE enables very large model capacity at lower inference cost—Mixtral and GPT-4 are believed to use this approach.

Model Compression

A set of techniques—including quantization, distillation, pruning, and low-rank factorisation—that reduce model size and computational requirements while preserving performance. Model compression is essential for deploying powerful models on edge hardware or within cost budgets.

Inference

The process of running a trained model on new data to produce predictions or generated outputs. Inference cost and latency are the dominant operational concerns in production AI, particularly for large generative models that can cost cents per request at scale.

Knowing the Terms Is Step One. Applying Them Is Step Two.

Book a Physical AI Fit Call to discuss how these AI concepts translate to your specific industry and business challenges.