NVIDIA Open-Sources Nemotron 3.5 Lightning for High-Volume Agentic Execution
NVIDIAAI · x · 2026-08-11
NVIDIA has fully open-sourced the Nemotron 3.5 Lightning model, built specifically for the high-volume execution tasks of long-running agents. The model is now available on Hugging Face.
The release includes not just the model weights, but also the data and training recipes. Featuring a 30B MoE architecture (with 3B active parameters) and a 1M token context length, it aims to deliver efficient agentic execution at a lower cost.
Related event: NVIDIA Open-Sources Nemotron Model and Agent Router(37 posts)→
More from Models
- Frontier Models' Biggest Bottleneck is 'Lack of Self-Esteem' in Math Research — coherence · 2026-08-12
- Pokee-Isaac 28B Beats Meta and Qwen Rivals in Sub-30B Agent Benchmarks — Kyrannio · 2026-08-12
- Post-Trained NVIDIA Nemotron Beats Claude Opus in Legal Agent Tasks — ctnzr · 2026-08-12
- New LLM Jailbreak Trick: Just Tell It to "Be Smarter Than Grok" — npinto · 2026-08-12
- MiniMax-H3-Turbo-Lora Lands on Hugging Face Trending Spaces — MiniMaxAI · 2026-08-12
- Simon Willison: Muse Glimmer is Meta's First Apache 2.0 Model — pcuenq · 2026-08-12