Small release, one new model. Ollama 0.40.10 adds Nemotron 3.5 Bolt E4B.
What’s new
- Nemotron 3.5 Bolt E4B is the smaller, Gemma 4-based vision-language model in the Nemotron 3.5 Bolt family, aimed at “fast local conversations, image understanding, and tool use.”
- It supports a 128K-token context window.
- Run it with:
ollama run nemotron-3.5-bolt:e4bReview before you install. This is a brand-new model tag. Before you pull it, read its page on ollama.com and check the size, the license and who published it. Make sure you have the disk space, and test on a machine without sensitive data first.
My take
A small vision model with tool use and a big context window is exactly the kind of thing I want for local agents. I covered the bigger Bolt and Super models back in Ollama 0.40.5. I’ve got a generic checklist for trying it here.
Have a blessed day! And Happy Hacking!
