ainewsblitz.com

Breaking

OpenAI Says Jalapeño Chip Beats Nvidia GB200 and GB300 on Inference Efficiency

  • Infra & Chips

OpenAI on Tuesday published the first public benchmarks for Jalapeño, saying its Broadcom-co-developed inference ASIC outperformed Nvidia GB200 and GB300 rack systems on work per watt and response speed across three open models. The figures were presented at the Hot Chips conference and in a company technical post.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,529 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year