Skip to content
AI Model Radar

NVIDIA Nemotron 3.5 Lightning 30B A3B BF16

nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
Open Source · chat · open-weights
Open Alert me on changes
Context
1M
Max output
65.5K
Weights
Open
API $/1M
$0.05 / $0.20
Modalities
text
Released
01 Aug 2026
License: other · nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
Download image Share on X Share on LinkedIn
AI summary
● machine-written

NVIDIA Nemotron 3.5 Lightning 30B: 1M context open-weights model

NVIDIA Nemotron 3.5 Lightning 30B-A3B is an open mixture-of-experts model with 3B active parameters out of 30B total, designed for high-throughput agentic workloads and domain-specific tasks. The model supports a 1M token context window and 65.5K maximum output, making it suited for extended document processing and specialized applications.

What's new
  • 1M token context window for extended inputs
  • Open-weights architecture with 3B active parameters
  • Maximum output of 65.5K tokens
  • Available as free tier on OpenRouter with multiple routing modes
Best for
High-throughput agentic workloadsDomain-specific task customizationExtended context document processingTool-calling and structured output applications
Sources

Source: https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16