Cerebras runs trillion-parameter OpenAI models internally
Cerebras operates trillion-parameter models developed by OpenAI on its dedicated inference hardware. These systems currently handle versions 5.4 and 5.5 exclusively for internal purposes at the AI firm. Company leadership indicates the infrastructure accommodates models of arbitrary scale without size restrictions.
@zephyr_z9 There could be specific demand for fast/costly model but yeah harder bet if you lock on specialized hardware.
Zephyr@zephyr_z9"We're serving trillion parameter models that are internal for OpenAI today. We are currently running OpenAI 5.4 and 5.5 with them" GPT 5.4/5.5 running internally to accelerate R&D and product development for OpenAI is very different from it being commercially viable for external inference at a trillion parameter scale
#1497Zephyr@ZEPHYR_Z9"We're serving trillion parameter models that are internal for OpenAI today. We are currently running OpenAI 5.4 and 5.5 with them"
GPT 5.4/5.5 running internally to accelerate R&D and product development for OpenAI is very different from it being commercially viable for external inference at a trillion parameter scale
Ray Wang@rwang07Cerebras CFO: "We serve all models, and there is no limit to the size of the models that we can serve. Today, we're serving trillion parameter models. We're serving trillion parameter models that are internal for OpenAI today. We are currently running OpenAI 5.4 and 5.5 with them."