root@fr:~$ lexique/quantification

Quantification

Models

Compressing a model by lowering the numerical precision of its parameters, so it runs faster and on more modest hardware, at the price of a limited quality loss. Together with distillation, it is one of the techniques that bring a large model within reach of infrastructure you control.

Also called Quantization, Quantisation

Related terms

Distillation de modèle

Models

A technique where a large model teaches a smaller one, which inherits part of its quality at a far lower cost and footprint. It makes it possible to run a...

Inférence

Models

Running an already trained model: it receives a request and produces its answer, token by token. It is the phase that runs day after day and carries the...

Modèle open-weight

Models

An AI model whose weights are released and can be downloaded, run and adapted on your own infrastructure. It enables self-hosting and execution sovereignty,...

Does this notion touch your business?

Go from definition to deployment: a first agent on your data, in France, on a model you control end to end.

The right model Let's talk about your AI