Get the latest tech news

GPT-OSS 120B Runs at 3000 tokens/sec on Cerebras

Cerebras is the go-to platform for fast and effortless AI training. Learn more at cerebras.ai.

None

Related news:

Cerebras Code now supports GLM 4.6 at 1000 tokens/sec

Why Nicholas Thompson Made a Custom GPT to Run Faster

Compiler optimizations for 5.8ms GPT-OSS-120B inference (not on GPUs)