Confirmed
NVIDIA releases Nemotron 3.5 Bolt E4B, a 4GB post-trained Gemma 4 E4B model
NVIDIA says Bolt E4B offers about 40% higher average quality than its prior model on conversational agent benchmarks and outputs up to about 80% fewer tokens than peers. It targets voice and device assistants on RTX, Jetson and DGX Spark hardware.
Every outlet that ran it 1 article
r/LocalLLaMACommunityLead