NVIDIA Launches Nemotron 3.5 Lightning: 30B Parameter AI Model Runs 30% Faster Than Competitors With Only 3B Active Parameters

NVIDIA launches Nemotron 3.5 Lightning, a 30B parameter open Mixture-of-Experts AI model that activates only 3B parameters at a time, delivering up to 4x faster output speeds and completing 10,000 agentic tasks 30% faster than Qwen3 35B, with fully open weights released under OpenMDW-1.1 for deployment anywhere from local hardware to data centers.

• NVIDIA Nemotron 3.5 Lightning is a 30B parameter open Mixture-of-Experts model with only 3B active parameters, purpose-built for high-volume, low-latency execution in always-on AI agents handling tasks like tool calls, result validation, and subagent delegation.
• The model delivers up to 4x output speed compared to similar-sized models and completes 10,000 agentic tasks 30% faster than Qwen3 35B at comparable accuracy, powered by speculative decoding, harness-optimized training, and NVFP4 and BF16 quantization checkpoints.
• NVIDIA NeMo Switchyard now enables intelligent model routing, allowing Nemotron 3.5 Lightning to serve as an efficient execution-layer target alongside frontier models, with fully open weights, training data, and recipes released under OpenMDW-1.1 for broad customization and deployment anywhere from local hardware to data centers.