Article

RockAI Matrix open-sources EdgeRock-4B: KV Cache does not grow with context, single-card throughput reaches 6.42x the original model

RockAI Matrix, under RockAI Technology, together with universities including the Hong Kong University of Science and Technology and Carnegie Mellon University, released and open-sourced EdgeRock-4B. The model is converted from Qwen3.5-4B, and its core is the Memory Rock Anchor (RMA) mechanism proposed by the team, which keeps the KV Cache from growing with context.

Part of the event: YanCore Matrix Open-Sources EdgeRock-4B Fixed-Memory Model

This page provides a summary and source link only.