8 text
NVIDIA's open 30B MoE built for high-throughput agentic workloads.
NVIDIA's open frontier reasoning model for orchestration, coding, and deep research.
NVIDIA's efficient 30B MoE Nemotron model with 3B active parameters.
NVIDIA's largest Nemotron model based on Llama 3.1 at 253B scale.
NVIDIA's mid-size Nemotron model based on Llama 3.3 at 49B scale.
NVIDIA's compact 12B vision-language Nemotron model.
NVIDIA's 70B Nemotron model based on Llama 3.1.
NVIDIA's open 30B MoE model with strong reasoning and agentic ability.
