M3 Ultra Runs DeepSeek R1 With 671 Billion Parameters Using 448GB Of Unified Memory, Delivering High Bandwidth Performance At Under 200W Power Consumption, With No Need For A Multi-GPU Setup
Take note that the smaller AI models run consistently and smoothly without using the full resources, but the DeepSeek R1 model with 671 billion parameters requires Apple's highest configuration of the M3 Ultra chip - a whopping 512GB. However, macOS imposes a limitation on VRAM allocation by default, and Dave Lee had to increase the limit manually through the Terminal, bumping it up to 448GB.