> ## Content Index
> Fetch the complete content index at: https://www.ai-360.online/llms.txt
> Use this file to discover other available public pages before exploring further.

# Cerebras launches Llama 4 inference at over 2,600 tokens per second
- URL: https://www.ai-360.online/cerebras-launches-world-s-fastest-inference-for-meta-llama-4/
- Published: 2025-04-09T12:00:00.000Z
- Updated: 2026-11-05T14:19:52.000Z
- Description: Cerebras launched Llama 4 inference on its CS-3 systems and cloud, citing over 2,600 tokens per second on Llama 4 Scout as measured by Artificial Analysis.
- Author: Nicholas Lipinski
- Tags: News, #company-cerebras, 1. Enterprise AI, Product

[Cerebras said on 9 April 2025](https://www.cerebras.ai/press-release/llama4PR?ref=ai-360.online) that it had launched Meta Llama 4 inference across its CS-3 systems and on-demand cloud platform.

Artificial Analysis measured [Cerebras](https://www.ai-360.online/cerebras/) at over 2,600 tokens per second on Llama 4 Scout, which Cerebras said is 19 times faster than the fastest GPU solutions. It also measured an end-to-end response time of 0.5 seconds.

Llama 4 is available on Cerebras through API access from US-based data centres and through [Hugging Face](https://www.ai-360.online/hugging-face/). “We’re thrilled to expand our partnership and bring this capability to millions of developers building the future of open AI,” said Clement Delangue, CEO of Hugging Face.

Cerebras said its architecture stores all model parameters in on-chip SRAM, which removes memory-transfer bottlenecks.

Llama 4 is [Meta](https://www.ai-360.online/meta/)’s open-weight model family with a Mixture of Experts architecture, which activates only a subset of parameters per token.

---