Cerebras unveils CS-4 server hardware for faster AI chatbot inference
Cerebras announced the CS-4 server hardware with dinner-plate-sized chips, claiming up to 30x faster AI chatbot query performance versus NVDA and AMD GPU setups, doubling CS-3, and delivering 10x throughput per watt.
CBRS announced a new version of its server hardware that includes its dinner-plate-sized chips that it says will speed AI chatbot queries.
CBRS unveiled the CS-4, claiming up to 30x faster than NVDA and AMD GPU setups while doubling the CS-3 and delivering 10x the throughput per watt.
Cerebras makes AI hardware and chips that compete with Nvidia (NVDA) and targets the portion of AI called inference, the Computing process of generating an answer in a chatbot such as Anthropic’s Claude.