OpenAI's Jalapeño chip beats Nvidia in inference benchmarks
OpenAI's custom inference chip Jalapeño delivered 1.5–1.9x more AI work per watt and 1.7–3.6x lower latency than Nvidia's GB200/GB300 on the InferenceX benchmark. Developed with Broadcom, it deploys in small volumes by end of 2026, ramping in 2027.
Featured · Richard Ho
How this story unfolded
3 days · 5 reports · 3 community posts · from Aug 22
- Aug 22
- Aug 25
OpenAI says its Jalapeño chip can power faster AI responses than the competitiontheverge.com
OpenAI built a chip in nine months. Then it let AI rewrite the code.thenewstack.io
OpenAI Claims Its New Chips Can Outperform Nvidia Processors in Testsbloomberg.com
OpenAI’s Jalapeño chip is built for fast inference at scale, benchmarks showtechcrunch.com
Jalapeño’s first results show industry-leading speed and efficiency in AI inferenceopenai.com
OpenAI by email
Get an email when OpenAI has news
No news that day, no email.
More stories today
- Stability AI raises $232M backed by music and gaming giants
- a16z podcast explores AI's impact on computing's evolution
- AI adoption lags in legal due to fragmented data foundations
- Bain & Company joins Claude Partner Network as Global Premier partner
- AI safety startup Alice raises $140M