AI Dynamics

Global AI News Aggregator

About

Cerebras Inference: 2200 tokens/sec on Llama 3.3 70B

What will you build in 2025 with the world's fastest Inference? Cerebras Inference by the numbers: Blazing fast 2200 tk/s on Llama 3.3 70B. Record-breaking 969 tk/s on Llama 3.1 405B. 70x faster than GPUs. Try it today: http://
chat.cerebras.ai

→ View original post on X — @cerebras