Apertus LLM Family Expansion via Distillation and Quantization

Andrei Panferov, Davit Melikidze, Martin Jaggi, Dan Alistarh
May, 2026
PDF Cite Paper

Abstract

Expanding the Apertus model family through distillation and quantization to support a broader range of model sizes and hardware budgets.

Type
Preprint
Publication
arXiv preprint
Andrei Panferov
Andrei Panferov
PhD Candidate in Computer Science

I work on efficient large language models, with a focus on low-precision training, quantization, and scaling laws.