Nano

Nemotron 3 Nano is a compact, open large language model in NVIDIA’s Nemotron 3 family, designed for efficient agentic reasoning, conversational AI, and coding tasks. It uses a hybrid Mixture-of-Experts Mamba-Transformer architecture that activates only a small subset of parameters per token, enabling low-latency inference while maintaining strong accuracy and reasoning performance. It has approximately 31.6 billion total parameters with around 3.2 billion active (3.6 billion including embeddings), allowing it to achieve higher accuracy than previous Nemotron 2 Nano while using less computation per forward pass. Nemotron 3 Nano supports long-context processing of up to one million tokens, enabling it to handle large documents, multi-step workflows, and extended reasoning chains in a single pass. It is designed for high-throughput, real-time execution, excelling in multi-turn conversations, tool calling, and agent-based workflows where tasks require planning, reasoning, and more.

nanoCAD’s Construction Module extends the nanoCAD platform with AEC drafting utilities and a library of standard parametric elements. It is designed to automate the preparation of construction drawings and documentation. nanoCAD platform provides you with a full set of basic and advanced design tools for creating and editing 2D/3D objects. It offers multiple drawing and editing methods for most geometric elements. nanoCAD platform is the base on which you build a more powerful CAD system to your specifications. nanoCAD’s Construction Module adds AEC drafting utilities to the nanoCAD platform, along with a library of standard parametric elements. It is designed to automate the preparation of construction drawings and documentation in the architecture, engineering, construction sector.