NVIDIA
Ctrl+K

Deploy Models Now with NVIDIA NIM

Optimized inference for the world’s leading models
Free serverless APIs for development
Accelerated by DGX Cloud
Self-Host on your GPU infrastructure
Continuous vulnerability fixes

Discover

Start Building with your DGX Spark

Explore step-by-step playbooks, including setting up NemoClaw, your secure personal AI agent.

Start Now

Featured Models

View All

The leading open models built by the community, optimized and accelerated by NVIDIA's enterprise-ready inference runtime.

Moonshotai
Downloadable

kimi-k2.5

1T multimodal MoE for high‑capacity video and image understanding with efficient inference.
Model
Mixture-of-Experts
2mo
NVIDIA
Downloadable

nemotron-3-super-120b-a12b

Open, efficient hybrid Mamba-Transformer MoE with 1M context, excelling in agentic reasoning, coding, planning, tool calling, and more
Model
Chat
2w
Minimaxai
Downloadable

minimax-m2.5

MiniMax M2.5 is a 230B-parameter text-to-text AI model excelling in coding, reasoning, and office tasks.
Model
coding
1mo
Z.ai
Downloadable

glm-5

GLM-5 744B MoE enables efficient reasoning for complex systems and long-horizon agentic tasks.
Model
Agentic
1mo

Design Custom Datasets

Create high-quality, domain-specific synthetic datasets at scale with NeMo Data Designer.

Start Now