# NVIDIA — Available now: NVIDIA Nemotron 3.5 Bolt E4B 4GB ⚡️

- Company: NVIDIA (nvidia.com)
- Announced: 2026-10-23T15:41:40+00:00
- Category: open-weight-release
- Coverage: not counted
- Announcement: yes
- Group: models
- Source: https://x.com/NVIDIAAI/status/2113657112408785153
- Record: https://forck.live/items/27175-available-now-nvidia-nemotron-3-5-bolt-e4b-4gb
- Open weights: yes
- Models affected: NVIDIA Nemotron 3.5 Bolt E4B 4GB, NVIDIA Cosmos

NVIDIA has made Nemotron 3.5 Bolt E4B 4GB available, a small open model it says is built for local assistants, interactive characters and robots that can hold a conversation and use tools. NVIDIA describes it as its newest small open model, positioning it for on-device work rather than cloud serving. In a demonstration, Reachy Mini chats and moves with Bolt handling conversation and NVIDIA Cosmos handling vision, and NVIDIA says both models run locally on Jetson Orin Nano 8GB. The post gives no license, context window or price for the model.

## Evidence

Verbatim from https://x.com/NVIDIAAI/status/2113657112408785153:

> Our newest small open model is built for local assistants, interactive characters and robots that can carry on a conversation and use tools to get things done.

## Follow-ups

- MarkTechPost (reported, 24 Oct): NVIDIA Releases Nemotron 3.5 Bolt E4B 4GB: An Open Small Language Model for Local Voice Agents, Game Characters and Robots — https://forck.live/items/27355-nvidia-releases-nemotron-3-5-bolt-e4b-4gb-an-open-small-language-model-for

---

Record: https://forck.live/items/27175-available-now-nvidia-nemotron-3-5-bolt-e4b-4gb
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md