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

DevFeed: [NVIDIA Releases Nemotron 3.5 Bolt E4B 4GB: An Open Small Language Model for Local Voice Agents, Game Characters and Robots](<https://devfeed.tech/articles/nvidia-releases-nemotron-3-5-bolt-e4b-4gb-an-open-small-language-model-for-local-voice-agents-game-characters-and-robots-98662.md>)

Original publisher: [Read original article](<https://www.marktechpost.com/2026/10/23/nvidia-nemotron-3-5-bolt-e4b-4gb/>)

Author: Asif Razzaq

Published: 2026-10-24T03:56:29Z

Content type: release

Language: en

Sources: [MarkTechPost](<https://devfeed.tech/sources/marktechpost.md>)

Topics: [Nemotron](<https://devfeed.tech/topics/nemotron.md>), [Local AI](<https://devfeed.tech/topics/local-ai.md>), [Conversational AI](<https://devfeed.tech/topics/conversational-ai.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [post-training](<https://devfeed.tech/topics/post-training.md>), [rlvr](<https://devfeed.tech/topics/rlvr.md>), [llama.cpp](<https://devfeed.tech/topics/llama-cpp.md>), [LLM optimization](<https://devfeed.tech/topics/llm-optimization.md>), [NeMo](<https://devfeed.tech/topics/nemo.md>), [Cosmos](<https://devfeed.tech/topics/cosmos.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [ai-paper-summary](<https://devfeed.tech/tags/ai-paper-summary.md>), [ai-shorts](<https://devfeed.tech/tags/ai-shorts.md>), [applications](<https://devfeed.tech/tags/applications.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [audio-language-model](<https://devfeed.tech/tags/audio-language-model.md>), [bolt](<https://devfeed.tech/tags/bolt.md>), [editors-pick](<https://devfeed.tech/tags/editors-pick.md>), [enterprise-ai](<https://devfeed.tech/tags/enterprise-ai.md>), [for-devs](<https://devfeed.tech/tags/for-devs.md>), [game](<https://devfeed.tech/tags/game.md>), [harness](<https://devfeed.tech/tags/harness.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [local](<https://devfeed.tech/tags/local.md>), [nemotron](<https://devfeed.tech/tags/nemotron.md>), [nemotron-3-5](<https://devfeed.tech/tags/nemotron-3-5.md>), [nemotron-3-5-bolt](<https://devfeed.tech/tags/nemotron-3-5-bolt.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [open](<https://devfeed.tech/tags/open.md>), [releases](<https://devfeed.tech/tags/releases.md>), [robots](<https://devfeed.tech/tags/robots.md>), [small](<https://devfeed.tech/tags/small.md>), [small-language-model](<https://devfeed.tech/tags/small-language-model.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>), [staff](<https://devfeed.tech/tags/staff.md>), [tech-news](<https://devfeed.tech/tags/tech-news.md>), [technology](<https://devfeed.tech/tags/technology.md>), [uncategorized](<https://devfeed.tech/tags/uncategorized.md>), [vision-language-model](<https://devfeed.tech/tags/vision-language-model.md>), [voice](<https://devfeed.tech/tags/voice.md>), [voice-agents](<https://devfeed.tech/tags/voice-agents.md>), [voice-ai](<https://devfeed.tech/tags/voice-ai.md>)

## AI overview

NVIDIA's Nemotron 3.5 Bolt E4B is an open, locally deployable conversational model post-trained from Gemma 4 E4B with reinforcement learning and no supervised fine-tuning. It targets voice assistants, game characters and embedded agents, with multi-turn tool use, speech-ready replies, configurable reasoning and a 64K context. NVIDIA reports Q4_K_M VRAM use of 3.1-4.3 GB on RTX tests, though the GGUF file is 6.18 GB. In NVIDIA's benchmark harness it led 15 of 21 comparisons, including IHEval, but trailed Qwen3.5-4B on Tau2-Bench, RULER 64K, LongBench v2 and BFCL-v3. On an RTX 5070, NVIDIA measured 272.6 tokens/s with its DFlash drafter versus 225.9 for Gemma 4 E4B with MTP. Results are vendor-measured and vary by capability; the model is offered through several local runtimes and NVIDIA deployment tools.

## Source excerpt

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. The post NVIDIA Releases Nemotron 3.5 Bolt E4B 4GB: An Open Small Language Model for Local Voice Agents, Game Characters and Robots appeared first on MarkTechPost.