Nemotron 3.5 Bolt E4B 4GB
Nemotron 3.5 Bolt E4B 4GB is a quantized text-generation model post-trained by NVIDIA from Gemma-4-E4B-it, with 8B total parameters and 4B effective parameters. It is designed for low-memory, low-time-to-first-token operation and emphasizes multi-turn tool use, instruction following, and input grounding.
What it does
Use it to build local voice and device assistants, interactive personas, and embedded interfaces.
- Availability
- GA (10/23/2026); available on Hugging Face
- Pricing model
- Not established
- Deployment
- llama.cpp
- Privacy
- Not established
- Licence
- OpenMDW License Agreement, version 1.1
Capability
Modality
Access
Deployment
Pricing
Target user
Evidence
9 claims- It was post-trained from Gemma-4-E4B-it and is intended primarily for customization and post-training rather than direct production inference.
- The model can be served with vLLM.
- The model is ready for commercial or non-commercial use under the OpenMDW License Agreement, version 1.1.
- The model improves multi-turn tool use, instruction following, and input grounding. [2]
Nemotron-3.5-Bolt-E4B carries forward Gemma’s strong conversational capabilities and further improves multi-turn tool use, instruction following, and input grounding for fast local voice/device assistants, interactive personas, and embedded/edge interfaces.
NVIDIA. Quoted text is outside CC BY 4.0 and keeps its original rights. - The model is available on Hugging Face and Build.NVIDIA.com. [2]
For more details on how to deploy and use the model — see the [Quick Start Guide](#quick-start-guide) below!
NVIDIA. Quoted text is outside CC BY 4.0 and keeps its original rights. - The model can be deployed with llama.cpp. [2]
- The model supports input and output context lengths up to 64K tokens. [2]
| **Context Length** | Input: up to 64K tokens; output: up to 64K tokens |
NVIDIA. Quoted text is outside CC BY 4.0 and keeps its original rights. - The model is designed for local voice and device assistants, interactive personas, and embedded interfaces. [2]
Nemotron-3.5-Bolt-E4B carries forward Gemma’s strong conversational capabilities and further improves multi-turn tool use, instruction following, and input grounding for fast local voice/device assistants, interactive personas, and embedded/edge interfaces.
NVIDIA. Quoted text is outside CC BY 4.0 and keeps its original rights. - The model is ready for commercial or non-commercial use under the OpenMDW License Agreement, version 1.1.
Sources
2
1
NVIDIAOwner-controlled
https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16
Retrieved 2026-10-29 00:08 UTC
Verified
2
NVIDIAOwner-controlled
https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB
Retrieved 2026-10-29 00:08 UTC
Verified
Versions
5| Version | Effective | Change | Changed fields | State |
|---|---|---|---|---|
| 5 | 2026-10-29 00:08 UTC | evidence update | score | Current |
| 4 | 2026-10-29 00:08 UTC | material change | capability, access, deployment, availability, deployment | Current |
| 3 | 2026-10-27 00:06 UTC | material change | capability, deployment, availability, deployment | Current |
| 2 | 2026-10-27 00:06 UTC | material change | access, availability | Current |
| 1 | 2026-10-25 18:00 UTC | publication | None | Current |
In briefs
2- A toolkit for voice agents that listen, respond, and take action Weekly brief 2026-W43
- AWS Continuum can investigate code vulnerabilities and propose fixes Daily brief 2026-10-25
Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.