Category

Efficiency

Smaller, faster and cheaper AI: research on compression, quantisation, distillation and efficient inference, and what it means for models in production.

Follow Efficiency
IIBenchmarkedPreprint

Claude Code agent designs LLM quantisation recipes that beat public baselines

An MIT and NVIDIA preprint lets a coding agent search for the best way to compress each reasoning model. It gains about one to two accuracy points over the strongest public recipes for an 8-hour search on 8 GPUs, and slightly beats NVIDIA's own compressed release of a 320B model.