NVIDIA Nemotron 3.5 Lightning Delivers Fast, Accurate Specialized Task Execution for Long-Running Agents | NVIDIA Technical Blog
NVIDIA Nemotron 3.5 Lightning is a 30B parameter, open Mixture-of-Experts (MoE) model with 3B active parameters, specifically optimized for high-volume, low-latency execution in always-on AI agents and agentic workflows.The model includes features like speculative decoding, harness-optimized training, and quantization (NVFP4 and BF16 checkpoints) to deliver strong accuracy with up to 4x output spe
1
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
処理を実行中です
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
nvda-20260817
Bristol Myers Squibb Building Life Science Industry’s Most Advanced AI Factory on NVIDIA Vera Rubin 
CUDA Toolkit 13.4 Developer Preview Release Notes — Release Notes 13.4 documentation
OpenAI is building software to break free from Nvidia's grip on AI infrastructure
