Cadence and Nvidia unveil Maestro AI models to automate chip design

Cadence launched its Maestro AI model family, fine-tuned on Nvidia's Nemotron to work with its own EDA tools. Early testing showed up to 30% better output quality and up to 5x greater token efficiency than general-purpose models. Cadence says 20–30% of chips in development today are designed with AI agents.

• Maestro is fine-tuned on Nvidia Nemotron for Cadence tools
• Up to 30% better quality and up to 5x token efficiency
• 20–30% of chips in development use AI agents
• Models run via API, in a secure VPC or on premises