Cerebras beats NVIDIA Blackwell: Llama 4 Maverick Inference Products Customers Partners Developers Resources Pricing Company Contact us Get Started May 28 2025 Cerebras Beats NVIDIA Blackwell in Llama 4 Maverick Inference At over 2,500 t/s, Cerebras has set a world record for LLM inference speed on, the company said on 28 May 2025.
Cerebras Breaks the 2,500 Tokens Per Second Barrier with Llama 4 Maverick 400B SUNNYVALE CA – May 28, 2025 -- Last week, Nvidia announced that 8 Blackwell GPUs in a DGX B200 could demonstrate 1,000 tokens per second (TPS) per user on Meta’s Llama 4 Maverick. Today, the same independent benchmark firm Artificial Analysis measured Cerebras at more than 2,500 TPS/user, more than doubling the performance of Nvidia’s flagship solution. “Cerebras has beaten the Llama 4 Maverick inference speed record set by NVIDIA last week,” said Micah Hill-Smith, Co-Founder and CEO of Artificial Analysis.
“Cerebras has beaten the Llama 4 Maverick inference speed record set by NVIDIA last week,” said Micah Hill-Smith, Co-Founder and CEO of Artificial Analysis. Artificial Analysis has benchmarked Cerebras' Llama 4 Maverick endpoint at 2,522 tokens per second, compared to NVIDIA Blackwell's 1,038 tokens per second for the same model.
For enterprise buyers, the useful next step is to map the claim to controls, data residency and measurable outcomes—and to ask for evidence on failure modes, oversight and auditability before treating the release as production-ready fact.