Back to NewsCerebras — Fastest Inference PlatformFebruary 12, 2025HardwareCerebra is currently the fastest inference platform, gets us to 1,200 tokens/s - 10x faster than any comparable models, and 3x faster than groq, using DeepSeek-R1-Distill-Llama-70B. https://x.com/CerebrasSystems/status/1885444050859487324RelatedTop Use of Claude Inference Is for EngineeringNumber of H100s Bought in 2024Microsoft Launches Quantum Chip Majorana 1PrevMistral Ships Le ChatNextSFT Memorizes, RL Generalizes
