Nemotron 3.5 Lightning

Released on August 11, 2026

Changes from previous version

A compact execution-tier follow-on after flagship Nemotron 3 Ultra: far fewer active parameters, much higher output speed, and more than 3x Nemotron 3 Nano on Terminal-Bench 2.1.

Release Summary

NVIDIA's open 31.6B-total, 3.6B-active hybrid MoE for high-volume agent execution. Successor to Nemotron 3 Nano in the small-model slot: OpenMDW-1.1 weights, 1M-token context, NVFP4 plus DFlash/DSpark speculative decoding, and 24.58 on Terminal-Bench 2.1 versus Nano's 8.29. NVIDIA positions it as the fast execution layer beside Nemotron 3 Ultra for planning.

Timeline

August 11, 2026

Nemotron 3.5 Lightning released

NVIDIA publishes Lightning weights on Hugging Face and ModelScope, with NIM, OpenRouter, and local DGX Spark serving.