NVIDIA Releases Nemotron 3.5 Bolt E4B 4GB: An Open Small Language Model for Local Voice Agents, Game Characters and Robots

NVIDIA released Nemotron 3.5 Bolt E4B 4GB, a small language model optimized for local voice assistants, game NPCs, and robots on RTX, Jetson, and Spark hardware. It uses reinforcement learning post-training from Google's Gemma 4 E4B and supports multi-turn tool use with a 64K context window.