Happy Horse 1.0 is now on fal

nvidia/nemotron-3-nano-omni

Open, efficient reasoning model from NVIDIA. 30B A3B hybrid Transformer-Mamba MoE, built for enterprise agentic workflows.
Inference
Commercial use

Input

Additional Settings

Customize your input with more control.

Result

Idle
The image shows a golden retriever puppy sitting on a wooden floor.

What would you like to do next?

Your request will cost $0.01 per 1000 token.

Logs