People evaluating the specific 4B Nano artifact rather than its larger 30B sibling.
The exact tag includes a 3.97B model package, local run command and NVIDIA license text.
The shared README describes 30B mixture-of-experts architecture and active-parameter counts; those are not attributed to this 4B tag. Family language support and performance claims are not assumed to be exact 4B results. Tool use needs external execution.
No subscription or per-token hosted fee for local inference within permitted uses. Hardware, electricity and setup are separate. NVIDIA Open Model License Agreement applies. Review the attached terms before production or redistribution.
Install a current compatible Ollama version, review the exact license and run: ollama run nemotron-3-nano:4b. API refers to the local runtime endpoint, not a hosted API included with the weights.
© Chagto 2026. All rights reserved