NVIDIA releases Nemotron 3.5 Bolt E4B, an open model for local voice agents
NVIDIA announced Nemotron 3.5 Bolt E4B, an open small language model that runs locally on GeForce RTX, Jetson and Spark hardware. Post-trained from Google's Gemma 4 E4B with reinforcement learning only, it targets roughly 4GB of VRAM. NVIDIA says it led 15 of 21 benchmarks against rivals.
