Nemotron 3.5 Lightning

NVIDIA Nemotron 3.5 Lightning 30B-A3B-NVFP4 is a high-performance, latency-optimized large language model featuring a hybrid Mamba-2 and Mixture-of-Experts (MoE) architecture. Designed for efficient agentic workflows, it utilizes 30B total parameters with 3B active parameters per token to deliver fast, accurate execution for specialized tasks.

NVIDIA Nemotron 3.5 Lightning 30B-A3B-NVFP4 is a high-performance, latency-optimized large language model featuring a hybrid Mamba-2 and Mixture-of-Experts (MoE) architecture. Designed for efficient agentic workflows, it utilizes 30B total parameters with 3B active parameters per token to deliver fast, accurate execution for specialized tasks.

• 01Hybrid Mamba-2 and Mixture-of-Experts (MoE) architecture
• 0230B total parameters with 3B active parameters per token
• 031 million token context window
• 04Optimized for low-latency, high-throughput agentic tasks
• 05Native support for tool calling and reasoning control
• 06Commercial-ready under OpenMDW-1.1 license