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

What happened

NVIDIA released Nemotron 3.5 Bolt E4B 4GB, an open small language model post-trained from Gemma 4 E4B for local voice assistants, game characters and robots, targeting about 4GB of VRAM on RTX and Jetson. NVIDIA has just released Nemotron 3.5 Bolt E4B 4GB , an open small language model for fast conversational agents. NVIDIA is a semiconductor company based in Santa Clara.

It targets voice assistants, game NPCs and robot interfaces running locally on RTX, Jetson and Spark hardware. The model is post-trained from Google’s Gemma 4 E4B using reinforcement learning only.

For developers, this is agent behavior in about 4GB of VRAM. That leaves room for speech and vision models.

Runs on: GeForce RTX, Jetson, RTX Spark and DGX Spark. Performance: Top score on 15 of 21 benchmarks against Gemma 4 E4B, Qwen3.5-4B and Nemotron 3 Nano 4B (NVIDIA-measured).

Worst: Tau2-Bench 55.1, about 20 points behind Qwen3.5-4B at 75.1. Nemotron 3.5 Bolt E4B is a small language model from NVIDIA that powers local conversational agents.

It combines natural dialogue with multi-turn tool calling. NVIDIA lists 3 target workloads: device and voice assistants, interactive characters, and embedded or industrial agents.