Models · Updated 23 Oct, 10:47 pm IST
Ollama adds NVIDIA Nemotron 3.5 Bolt E4B model to v0.40.10
Why it matters for readers: It lets you try a vision-language model that handles long inputs and runs locally for privacy or speed.
- Ollama's v0.40.10 release adds Nemotron 3.5 Bolt E4B, described as a smaller Gemma 4–based vision-language model.1
- The model is intended for fast local conversations, image understanding, and tool use.1
- Nemotron 3.5 Bolt E4B supports a 128K-token context window for long inputs.1
- The release notes mention a DFlash draft included for speculative decoding.1
- Users can run the model locally with the command shown: ollama run nemotron-3.5-bolt:e4b.1
Get a brief like this every morning
Uzha reads hundreds of sources and gives you the stories that matter for your work, with every source linked. Free.
Get started