Tailored recommendationsThe PC builds shown across the site will be filtered and prioritised to match your chosen use-case.
03333 444 127
Tailored recommendationsPC builds across the site will be filtered to match your chosen use-case.
Glossary
Quantisation
Quantisation reduces the precision of an AI model's weights (often from 16-bit to 4-bit) so it fits in less VRAM and runs faster, with small quality loss. A 4-bit (Q4) Llama 3.1 70B model uses ~40GB VRAM instead of ~140GB at FP16.