NVIDIA releases Nemotron 3.5 Bolt E4B, a small open model for local voice agents
AINVIDIA has released Nemotron 3.5 Bolt E4B, an open small language model for local voice assistants, game characters and robot interfaces. Its Q4_K_M build used 3.1 to 4.3 GB VRAM on RTX in NVIDIA tests, and NVIDIA reports top scores on 15 of 21 benchmarks against Gemma 4 E4B, Qwen3.5-4B and Nemotron 3 Nano 4B. The article notes it trails Qwen3.5-4B on Tau2-Bench, 55.1 versus 75.1, and that the GGUF file is 6.18 GB.
Loading source posts…
Source details
MarkTechPost · Asif Razzaq · marktechpost.comPublished · added here
Original title: NVIDIA Releases Nemotron 3.5 Bolt E4B 4GB: An Open Small Language Model for Local Voice Agents, Game Characters and Robots