# Cerebras CS-4 发布：推理性能翻倍

- 来源：Chubby♨️ (@kimmonismus)
- 发布时间：2026-08-20 23:57
- AIHOT 分数：41
- AIHOT 链接：https://aihot.virxact.com/items/cmt1q5xoa04poroov0m35j0my
- 原文链接：https://x.com/kimmonismus/status/2090468333476860347

## AI 摘要

Cerebras 发布 CS-4，未换新制程，仅通过重新设计供电与散热将时钟速度翻倍，使 AI 推理性能近乎翻番。单晶圆提供 250 PFLOPs 算力、43.2 PB/s 内存带宽；单机柜集成三片晶圆，达 750 PFLOPs。在 GPT-OSS-120B 上，每用户每秒超 4,400 tokens，推理速度较 GPU 系统最高快 30 倍。

## 正文

This is seriously impressive: Cerebras just unveiled CS-4, and nearly doubled its AI inference performance without moving to a new process node.

Same gigantic 5nm wafer.
Same 4 trillion transistors.
Same 900,000 AI cores.
Instead, Cerebras redesigned the power delivery and cooling, allowing the wafer to run at twice the clock speed.
The result per WSE-3 Turbo:

• 250 PFLOPs of AI compute
• 43.2 PB/s of memory bandwidth
• 2.4 Tb/s of I/O bandwidth

A single CS-4 rack combines three wafers for 750 PFLOPs and 129.6 PB/s of memory bandwidth.

On GPT-OSS-120B, Cerebras reports more than 4,400 tokens per second per user, and up to 30x faster inference than GPU-based systems.

So yeah, intelligence not only too cheap to meter but also too fast to keep up with