Java Tech Enthusiast

Mar 18, 2025 · Artificial Intelligence

Can Apple’s M3 Ultra Mac Studio Run Full‑Scale DeepSeek R1 at 11 Tokens/s?

Early adopters benchmarked the M3 Ultra‑powered Mac Studio running the 671‑billion‑parameter DeepSeek R1 model, achieving around 11 tokens per second in practice (up to 20 tokens/s theoretically), and compared its performance and cost against GPU‑based solutions and the newer M4 Max hardware.