Gemma-4-E2B

A developer benchmarked AWS g5g and g6 GPU instances for serving Google's Gemma-4-E2B language model with identical code and weights, finding the g6 delivers 3.7x the decode throughput. Profiling reve…

IFlytek has released Domux, an open model built on Google's Gemma-4-E2B base, designed for smart-home command understanding at the edge. The model focuses on intent parsing and slot filling to convert…

Researchers presented AURA-ST, a three-stage modular pipeline for low-resource speech-to-text translation at IWSLT 2026. The system bypasses traditional cross-attention by treating projected acoustic …