Skip to content
Sign in
All terms
Glossary · Term

Quantization

L4 · ExpertEvolving

In plain terms

Storing model weights in fewer bits.

Technical definition

Representing weights and/or activations in lower precision (e.g. INT8/INT4 instead of FP16) to cut memory and bandwidth, usually with a small, measurable accuracy cost.

Example

Running a model in 4-bit so it fits on a smaller GPU.

Try it in the GPU / VRAM Calculator labExplore in the AI Universe

Related terms