Deployment

Model Compression

Definition

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.

Related Terms

Quantization

A model compression technique that reduces the numerical precision of model weights—for example, from 32-bit floats to 8-bit integers—shrinking memory requirements and accelerating inference with minimal accuracy loss. Quantization is essential for deploying LLMs on-premise or at the edge.

Knowledge Distillation

A training technique where a smaller "student" model is trained to replicate the behaviour of a larger "teacher" model. Distillation produces compact, fast models suitable for latency-sensitive or resource-constrained deployments without sacrificing too much quality.

Edge AI

Running AI models on edge devices—industrial controllers, cameras, vehicles, mobile phones—rather than in the cloud. Edge AI reduces latency, preserves data privacy, and enables operation in environments with limited connectivity, making it critical for physical AI deployments.

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.