# NVIDIA releases Nemotron 3.5 Bolt E4B for local voice agents and robots

Digest AI · Generative AI & Models · published 2026-10-24T03:56:29Z

Canonical: https://digestai.news/story/nvidia-releases-nemotron-3-5-bolt-e4b-for-local-voice-agents-and-robot

## Summary

NVIDIA released Nemotron 3.5 Bolt E4B 4GB, an open small language model designed for fast conversational agents running locally on GeForce RTX, Jetson, RTX Spark, and DGX Spark hardware. Post-trained exclusively from Google's Gemma 4 E4B using reinforcement learning rather than supervised fine-tuning, the model features 8B total parameters, 4B effective parameters, and a 64K token context window. In NVIDIA tests, a quantized Q4_K_M build consumed between 3.1 and 4.3 GB of VRAM.

According to NVIDIA's internal benchmarks across 21 evaluations, Bolt outperformed Gemma 4 E4B, Qwen3.5-4B, and Nemotron 3 Nano 4B on 15 tests in reasoning mode. It reached 84.8 on IHEval compared to Gemma's 67.0, though it trailed Qwen3.5-4B on Tau2-Bench with 55.1 versus 75.1. Using speculative decoding with a DFlash drafter on an RTX 5070, NVIDIA reports generation speeds reaching 272.6 tokens per second.

The model is licensed under OpenMDW-1.1 and is distributed on Hugging Face, Ollama, LM Studio, Unsloth, and Jetson AI Lab, alongside NVIDIA NIM and the In-Game Inferencing SDK. Although named '4GB' to reflect its memory footprint goal, the downloadable Q4_K_M GGUF file measures 6.18 GB.

## Key points

- NVIDIA launched Nemotron 3.5 Bolt E4B with 8B total and 4B effective parameters, fitting in roughly 4GB VRAM.
- Trained from Google's Gemma 4 E4B using reinforcement learning without supervised fine-tuning, featuring a 64K context window.
- NVIDIA claims it won 15 of 21 internal benchmarks against competing small models, reaching 272.6 tokens/s on an RTX 5070.

## Why it matters

Fitting conversational reasoning into roughly 4GB of VRAM allows developers to run speech, vision, and language agents simultaneously on consumer GPUs and edge devices.

## Sources

1. [NVIDIA Releases Nemotron 3.5 Bolt E4B 4GB: An Open Small Language Model for Local Voice Agents, Game Characters and Robots](https://marktechpost.com/2026/10/23/nvidia-nemotron-3-5-bolt-e4b-4gb) (MarkTechPost, 2026-10-24)
2. [With the arrival of NVIDIA Nemotron 3.5 Bolt E4B, those who delegate small tasks to local AI will benefit](https://note.com/unikoukokun/n/n0106026fc993?hl=en) (note.com, 2026-10-23)

Part of the developing story: [AI Model Showdown Coding to Voice](https://digestai.news/thread/recursive-releases-flint-40b-coding-agent-model-on-hugging-face) (2 stories)

## Cite

Digest AI, "NVIDIA releases Nemotron 3.5 Bolt E4B for local voice agents and robots", 24 October 2026, https://digestai.news/story/nvidia-releases-nemotron-3-5-bolt-e4b-for-local-voice-agents-and-robot

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/nvidia-releases-nemotron-3-5-bolt-e4b-for-local-voice-agents-and-robot.json