DeepSeek-V3 Now Runs At 20 Tokens Per Second On Mac Studio, And That’s A Nightmare For OpenAI

Published Date: Mon, 24 Mar 2025 19:50:58 GMT | By VentureBeat On https://venturebeat.com

Upcomingweb USA Technology Latest News - DeepSeek's free 685B-parameter AI model runs at 20 tokens/second on Apple's Mac Studio, outperforming Claude Sonnet while using just 200 watts, challenging OpenAI's cloud-dependent business model.