Skip to content

Optimizing for efficiency with IBM’s Granite

Practical AI

Hosted by Chris Benson

43m
Transcript

Original podcast

Where to listen

About this episode

We often judge AI models by leaderboard scores, but what if efficiency matters more? Kate Soule from IBM joins us to discuss how Granite AI is rethinking AI at the edge—breaking tasks into smaller, efficient components and co-designing models with hardware. She also shares why AI should prioritize efficiency frontiers over incremental benchmark gains and how seamless model routing can optimize performance. Featuring: Kate Soule – LinkedIn https://www.linkedin.com/in/katesoule/Chris Benson – Website https://chrisbenson.com/, GitHub https://github.com/chrisbenson, LinkedIn https://www.linkedin.com/in/chrisbenson, X https://x.com/chrisbensonDaniel Whitenack – Website https://www.datadan.io/, GitHub https://github.com/dwhitena, X https://x.com/dwhitenaLinks: IBM Granite https://www.ibm.com/graniteIBM Granite on Hugging Face https://huggingface.co/ibm-graniteIBM Expands Granite Model Family with New Multi-Modal and Reasoning AI Built for the Enterprise https://newsroom.ibm.com/2025-02-26-ibm-expands-granite-model-family-with-new-multi-modal-and-reasoning-ai-built-for-the-enterprise

Transcript

0:00
43:38

8,154 words · 4 speakers

Speaker names marked are inferred from speaking time and the show’s known hosts — they are not voice-verified.

Page updated · transcript and summary are machine-generated