On August 11 local time, NVIDIA announced the launch of the 30B open-source AI model Nemotron 3.5 Lightning, further expanding its Nemotron 3 model series.
According to NVIDIA, Nemotron 3.5 Lightning is a mixture-of-experts (MoE) model with 30 billion parameters, designed for specific tasks in large-scale multi-agent systems to help developers build more intelligent and efficient agent applications.
Compared with other models in the same category, the model can deliver up to 4x faster output, accelerating the overall completion of agent tasks by 30%.
Nemotron 3.5 Lightning can run directly on local AI systems, including NVIDIA RTX PCs, NVIDIA DGX Spark, NVIDIA DGX Station, and NVIDIA Jetson. It can also be seamlessly scaled for enterprise applications across edge AI devices, NVIDIA RTX PRO workstations, data centers, and cloud environments.
Open-source links:
Hugging Face: https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4
ModelScope: https://modelscope.ai/collections/nv-community/Nemotron-35-Lightning
OpenRouter: https://openrouter.ai/nvidia/nemotron-3.5-lightning:free
NVIDIA: https://build.nvidia.com/nvidia/nemotron-3.5-lightning-30b-a3b