CS-4 / Nexus platform
Cerebras' CS-4 wafer-scale AI system, the first built on its reusable Nexus rack-scale platform, unveiled at Supernova 2026.
Overview
Cerebras unveiled CS-4 on August 19, 2026 at its Supernova launch event in San Francisco, the first system built on Nexus, a reusable rack-scale platform housing three Wafer-Scale Engines per rack in modular 'compute backpacks.' On August 25, 2026 at Hot Chips, Cerebras detailed the Nexus rack architecture and previewed a roadmap: CS-5 (targeting 2027, higher tokens/sec per user) and CS-6 (3D-stacked wafer-scale DRAM).
This is a sourced directory entry. Features and capabilities are reported in the linked sources; this entry does not document independent Aymorphic testing.
Key features
- Nexus rack-scale platform hosting 3 Wafer-Scale Engines per rack
- Modular 'compute backpack' design
- Roadmap preview: CS-5 (2027) and CS-6 with 3D-stacked wafer-scale DRAM
- Claimed throughput uplift vs. prior CS-3 generation
Use cases
- Wafer-scale LLM inference/training at rack scale
- Frontier low-latency inference deployments
- AI datacenter rack buildouts
Pricing
unknown
Pricing reflects the source record and may change. Confirm current terms with the provider.
Dates and sources
- Released
- 19 Aug 2026
- Record updated
- 23 Sept 2026
- Record last checked
- 23 Sept 2026
- cerebras.ai/blog/ultrafast-frontier-inference-cerebras-deep-dive-at-hot-chips-2026
- tomshardware.com/tech-industry/artificial-intelligence/hot-chips-2026-cerebras-lays-out-the-future-of-wafer-scale-ai-nexus-system-architecture-triples-rack-scale-performance-cs-6-wafer-to-incorporate-stacked-dram
- servethehome.com/cerebras-talks-going-rack-scale-with-their-wses-at-hot-chips-2026/