# Ollama adds NVIDIA Nemotron 3.5 Bolt E4B in v0.40.10

> The new release (v0.40.10) lets Ollama run NVIDIA’s Nemotron 3.5 Bolt E4B, a fast, locally‑run vision‑language model with a 128K token window.

Oossa · 2026-10-23 · https://oossa.com/en/ollama-adds-nvidia-nemotron-3-5-bolt-e4b-in-v0-40-10

Ollama released version 0.40.10 on 23 Oct 2026. The update adds support for NVIDIA’s Nemotron 3.5 Bolt E4B model. The model is built on the Gemma‑4 architecture, works locally, and can handle image input, tool use, and long contexts up to 128 000 tokens. It also includes a DFlash draft for speculative decoding, which speeds up generation. Users can start it with ‘ollama run nemotron-3.5-bolt:e4b’.

## The facts

- Model: Nemotron 3.5 Bolt E4B (Gemma‑4 based)
- Context window: 128 000 tokens

## Why it matters

Local developers can now run a fast vision‑language model on their own machines without cloud calls.

## Sources & references

1. [ollama/ollama v0.40.10](https://github.com/ollama/ollama/releases/tag/v0.40.10-rc0) – Ollama, 2026-10-23
2. [ollama/ollama v0.40.10](https://github.com/ollama/ollama/releases/tag/v0.40.10) – Ollama, 2026-10-23

Last updated: 2026-10-23