Nemotron 3.5 Lightning
by NVIDIA · Model · Language & code models
NVIDIA released Nemotron 3.5 Lightning, a 30B mixture-of-experts model with 3B active parameters per token
AccessOpen weightsNeeds~75 GBSize30B parametersLicenseOpenMDW 1.1
Evidence
- Aug 12Served with vLLM using FlashInfer Mamba backend, FP16 Mamba state and stochastic rounding; used close to 75 GB VRAM, reducible via KV cache
- Aug 11Per NVIDIA's chart, does not win coding or terminal benchmarks against same-size peers; wins instruction following and long context
- Aug 11Sits near the bottom of the intelligence index, well behind Opus and Kimi K3 frontier models