---
type: "post"
id: "nvidia-released-nemotron-3-5-bolt-e4b-4gb-5d9d76"
slug: "nvidia-released-nemotron-3-5-bolt-e4b-4gb-5d9d76"
title: "NVIDIA released Nemotron 3.5 Bolt E4B 4GB , an open small model built on Gemma 4 E4B via RL post-training"
description: "NVIDIA has published NVIDIA-Nemotron-3.5-Bolt-E4B-4GB, a quantized local language model post-trained from Gemma 4 E4B-it."
retrieval_nugget: "NVIDIA has published NVIDIA-Nemotron-3.5-Bolt-E4B-4GB, a quantized local language model post-trained from Gemma 4 E4B-it."
published_at: "2026-10-24"
updated_at: "2026-10-24"
record_date: "2026-10-24"
date_kind: "published_at"
topics: ["local-models","open-models","models"]
entities: ["NVIDIA","NVIDIA-Nemotron-3.5-Bolt-E4B-4GB","Gemma 4 E4B-it","DFlash","llama.cpp","OpenMDW"]
related_patterns: []
novelty_label: "new_fact"
what_changed: "The Hugging Face release page specifies the 4GB Bolt E4B build: Gemma-4-E4B-it post-training, Q4_K_M quantization, and up to 64K-token input and output."
prior_refs: ["memory:1fe79f90-86ec-847a-ab74-1c640331fdbe","memory:6f3f8de8-ef52-829f-ab81-532d01fe7d9e","memory:aa6860cb-68d1-80db-ad83-1085c9ef07a6"]
source_url: "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB"
source_urls: ["https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:nvidia-released-nemotron-3-5-bolt-e4b-4gb-5d9d76"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/nvidia-released-nemotron-3-5-bolt-e4b-4gb-5d9d76/","markdown":"https://newruntime.com/posts/nvidia-released-nemotron-3-5-bolt-e4b-4gb-5d9d76.md","json":"https://newruntime.com/posts/nvidia-released-nemotron-3-5-bolt-e4b-4gb-5d9d76.json"}
---

# NVIDIA released Nemotron 3.5 Bolt E4B 4GB , an open small model built on Gemma 4 E4B via RL post-training

## Retrieval answer

NVIDIA has published NVIDIA-Nemotron-3.5-Bolt-E4B-4GB, a quantized local language model post-trained from Gemma 4 E4B-it.

NVIDIA has published NVIDIA-Nemotron-3.5-Bolt-E4B-4GB, a quantized local language model post-trained from Gemma 4 E4B-it. NVIDIA describes it as a model for local voice and device assistants, interactive personas, and embedded interfaces, with improved multi-turn tool use, instruction following, and input grounding.

The release uses Q4_K_M precision and lists 8B total parameters, with 4B effective parameters. It supports up to 64K input tokens and 64K output tokens. The model card specifies text input and output, chat-template controls for thinking and conversational modes, and commercial as well as non-commercial use under the OpenMDW-1.1 license.

NVIDIA provides llama.cpp launch commands and a companion DFlash drafter for speculative decoding. A full-precision BF16 variant is also linked. The card says a llama.cpp recipe is pending.

The source includes NVIDIA-run benchmark comparisons against Gemma, Qwen, and an earlier Nemotron Nano model. It does not establish independent benchmark results, performance on a particular device, or production reliability for an agent workload.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Local Models](https://newruntime.com/topics/local-models.md): Explore the local-models topic hub.
- topic hub: [Open Models](https://newruntime.com/topics/open-models.md): Explore the open-models topic hub.
- topic hub: [Models](https://newruntime.com/topics/models.md): Explore the models topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)