---
title: "NVIDIA releases Nemotron 3.5 Bolt, a 4GB open model for local voice agents"
url: https://www.parallelquant.com/posts/nvidia-releases-nemotron-3-5-bolt-a-4gb-open-model-for-local-voice-agent-226b5c
source_name: "MarkTechPost"
source_url: https://www.marktechpost.com/2026/10/23/nvidia-nemotron-3-5-bolt-e4b-4gb/
published: 2026-10-24T03:56:29.000Z
topics: ["open source", "llms", "chips"]
publisher: "Parallel Quant"
---

# NVIDIA releases Nemotron 3.5 Bolt, a 4GB open model for local voice agents

*2026-10-24 · Source: [MarkTechPost](https://www.marktechpost.com/2026/10/23/nvidia-nemotron-3-5-bolt-e4b-4gb/)*

NVIDIA released Nemotron 3.5 Bolt E4B 4GB, an open small language model post-trained from Gemma 4 E4B. It targets local voice assistants, game characters and robots, and is sized to run in about 4GB of VRAM on RTX and Jetson hardware.

**Why it matters:** Small on-device models that fit consumer GPUs and edge robotics boards push voice agents away from cloud APIs, cutting latency and cost. It also shows NVIDIA using open third-party bases to pull developers toward its own RTX and Jetson hardware stack.

**Topics:** open source, llms, chips

---
Read the original: https://www.marktechpost.com/2026/10/23/nvidia-nemotron-3-5-bolt-e4b-4gb/
Canonical: https://www.parallelquant.com/posts/nvidia-releases-nemotron-3-5-bolt-a-4gb-open-model-for-local-voice-agent-226b5c
Published by Parallel Quant — https://www.parallelquant.com