Summary & Key Takeaways ​

• NVIDIA Nemotron 3.5 Lightning is now available on Ollama.
• It's a 30 billion parameter open model, with 3B active parameters.
• The model is specifically designed for AI agents.
• It excels at continuous operation, context gathering, tool calling, and multi-step tasks.
• Users can run this powerful model on their own hardware via Ollama.

Our Commentary ​

This is a big one for the local AI scene. An open, agent-focused model from NVIDIA, easily runnable via Ollama? Yes, please. We're seeing a clear push towards more capable, locally deployable agents. The idea of an agent "staying running, gathering context" on my own hardware is both exciting and a little bit terrifying. The future is here, and it's on your GPU.