Ollama v0.40.10 adds NVIDIA's Nemotron 3.5 Bolt E4B

The October 23 release brings NVIDIA's smaller, Gemma 4-based vision-language model for fast local conversations, image understanding and tool use, with a 128K-token context and a bundled DFlash speculative-decoding draft.

AI News In FocusUpdated Oct 24, 2026 2 min read

Official source published Oct 23, 2026

Ollama released v0.40.10 on October 23, 2026. The single-item update adds NVIDIA's Nemotron 3.5 Bolt E4B to the model library. Read the release notes.

Nemotron 3.5 Bolt E4B

Nemotron 3.5 Bolt E4B is NVIDIA's smaller, Gemma 4-based vision-language model for fast local conversations, image understanding and tool use. It supports a 128K-token context window and ships with a DFlash draft model for speculative decoding:

ollama run nemotron-3.5-bolt:e4b

The full changelog lists only this model addition against v0.40.9. For the Nemotron 3.5 family background — the 120B Super and 74B Bolt variants added in v0.40.5 — see our v0.40.5 report; the speech and d3 additions are covered in our v0.40.9 report.