GoKawiil
Tech News
At the Hot Chips conference, OpenAI released the first benchmark results for Jalapeño, its custom AI inference chip built with Broadcom. On SemiAnalysis' InferenceX test, the chip beat current Nvidia Blackwell systems in tokens served per user and throughput per kilowatt of power. OpenAI plans small-scale deployment by late 2026, with broader rollout in 2027.
OpenAI has revealed details of Jalapeño, a custom inference chip developed with Broadcom over roughly 16 months, at the Hot Chips conference. SemiAnalysis tested the chip using its InferenceX benchmark suite and found it outperforms Nvidia, AMD, and Google chips across multiple open-source models, despite being OpenAI's first hardware effort.
OpenAI detailed benchmark results for its Jalapeño chip, an inference-focused ASIC built with Broadcom, claiming it outperforms Nvidia's GB200 and GB300 chips on efficiency and response speed. Using its InferenceX benchmark across models like GPT-OSS 120B, DeepSeek R1, and Kimi K2.5, OpenAI reported 1.5-1.9x more work per watt and up to 3.6x lower latency. Small-scale deployment is planned by year-end, with volume scaling into 2027.