LLM
GA
Open weights
Nemotron 3 Nano
Highly efficient helper model on a single GPU
Release2026-03
Context262K
Max output—
Parameters30B
Local / VRAM20–24 GB
LicenseOpen weights
Overview
Nemotron 3 Nano is a model in the LLM category from NVIDIA. It was released in 2026-03. The vendor is based in US. Best for: Highly efficient helper model on a single GPU.
Strengths
- 30B/3B MoE
- 256K context
- Single 4090
Limits
- No image input
- Not frontier reasoning
Specifications
| Vendor | NVIDIA |
|---|---|
| Category | LLM |
| Release | 2026-03 |
| Status | GA |
| License | Open weights |
| License name | NVIDIA Open Model License |
| Commercial use | Allowed |
| Parameters | 30B |
| Active parameters | 3B |
| Architecture | MoE transformer |
| Context window | 262K |
| Input modalities | Text |
| Output modalities | Text |
| Prompt types | Text |
| Negative prompts | No |
| Max outputs | 1 |
| Local deployment | Yes |
| VRAM | 20–24 GB |
| System RAM | 32–64 GB |
| API access | Yes |
| Pricing | Free weights |
| Confidence | Medium |
| Vendor country | US |
| Vendor type | Open lab |
Pricing & hardware
Free weights
This model can be self-hosted or run locally. Approximate GPU memory: 20–24 GB. Approximate system RAM: 32–64 GB. API access is available.