NVIDIA Launches Nemotron 3.5 Lightning: A 30B MoE Model Built for Agents
baseten · x · 2026-08-11
NVIDIA has released the Nemotron 3.5 Lightning model, now available on the Baseten platform. Distilled from the larger Nemotron 3 Ultra, this model is specifically designed for long-running agentic workflows. It features a 30B Mixture-of-Experts (MoE) architecture with only 3B active parameters and supports a 1 million token context length.
According to official and production testing data, the model delivers 4x higher throughput, 50% lower costs, and 63.4% fewer output tokens compared to similar-sized open models. Additionally, the CodeRabbit team fine-tuned this model using Baseten Training, achieving an 80.4% routing agreement, a 4.6% increase over the 75.8% baseline.
Related event: NVIDIA Open-Sources Nemotron 3.5 Lightning Model and NeMo Switchyard(24 posts)→
More from coding & agent
- Running opencode2 AI Coding Agent Inside Durable Objects — ritakozlov · 2026-08-11
- Open CLI Tool Installs 120 Curated Skills for AI Coding Agents — tom_doerr · 2026-08-11
- Building a Distributed, Event-Driven AI Agent Platform — blaizedsouza · 2026-08-11
- Agentic AI Architecture Cheat Sheet: 7-Layer Framework from Goal to Governance — blaizedsouza · 2026-08-11
- dhh predicts humans won't read or write code in 5 years, sparking debate — rohanpaul_ai · 2026-08-11
- Grok Build Adds Interactive /tour Tutorial for Terminal Learning — XFreeze · 2026-08-11