NVIDIA Launches Nemotron 3.5 Lightning: Open 30B MoE Model with 4x Output Speed
ctnzr · x · 2026-08-12
NVIDIA has officially released the Nemotron 3.5 Lightning model. It is an open-weights Mixture-of-Experts (MoE) model with 30 billion total parameters and 3 billion active parameters.
Built for "always-on" agents, the model is designed to complete high-volume, specialized tasks faster. NVIDIA claims it delivers up to 4x the output speed of similar-sized models. It can run efficiently on local hardware like the DGX Spark, while the larger Nemotron Ultra is available on Perplexity.
Related event: NVIDIA Unveils Nemotron 3.5 Lightning and NeMo Switchyard Router(55 posts)→
More from Infra
- Jensen Huang: Musk's AI buildout moved from K's to M's, now a CSP-tier NVIDIA customer — elonmusk · 2026-10-16
- EpochAI pegs GPT-6 training at up to 1.8e27 FLOP; scaling01 calls param estimates way too high — scaling01 · 2026-10-16
- Meta's Muse Spark Open scores 39 vs 48 for closed Spark 1.3 on AA Intelligence Index — EAccelerate_42 · 2026-10-16
- LLM spots useless 95GB-per-frame memcpy in ffmpeg dblur, cutting runtime from 2452ms to 49ms — IgorCarron · 2026-10-16
- DeepSeek-V4-Flash on 4x Radeon AI PRO R9700: the 'refused' 4-card config hits ~79 tok/s — brainchillzZ · 2026-10-16
- Tree packing lands in TRL's AsyncGRPO, cutting agentic RL training compute by over 26x — joecole · 2026-10-16