Inferbase
Beta
Nemotron 3 Nano 30B A3B (free)
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully open with open-weights, datasets and recipes so developers can easily customize, optimize, and deploy the model on their infrastructure for maximum privacy and security.
Input
Output
Context
256K
Max Output
—
Parameters
30B
Technical Specifications
Model TypeChat
Context Window256K
Max Output Tokens—
Parameters30B
Training Cutoff—
License—
Capabilities
Input Modalities
text
Output Modalities
text
Benchmarks
Pricing
per 1M tokens • updated regularlyPricing
Input
Free
Output
Free
Available on 1 Platform
| Platform | Input | Output |
|---|---|---|
OpenRouter | Free | Free |
Estimated GPU Requirements for Nemotron 3 Nano 30B A3B (free)
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Mar 24, 2026
Build Your AI Stack with Confidence
Explore models, compare pricing and benchmarks, and right-size your infrastructure — all in one place.