DeepSeek-V3 now runs at 20 tokens per second on Mac Studio, and that’s a nightmare for OpenAI

DeepSeek-V3 now runs at 20 tokens per second on Mac Studio, and that’s a nightmare for OpenAI

/in

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.Read More

Security News | VentureBeat – ​Read More

China-Nexus APT ‘Weaver Ant’ Caught in Yearslong Web Shell Atta...China-Nexus APT ‘Weaver Ant’ Caught in Yearslong Web Shell AttackMicrosoft’s new AI agents aim to help security pros combat the latest...