Tech Brew Ride Home · Tuesday, August 25, 2026
OpenAI claims its custom-designed 'Jalapeno' chip, developed with Broadcom, significantly outperforms Nvidia's chips in AI inference tasks. The chip reportedly delivers 1.5x to 1.9x more AI work per watt and 1.7x to 3.6x lower latency compared to Nvidia's GB 200 and GB 300 superchips across various AI models.
“Speaking of chips, Open AI says its jalapeno chip delivered 1.5X to 1.9X more AI work per watt and 1.7X to 3.6X lower latency than Nvidia chips across GPT-OS S, deep seek R1, K2.51T, quoting the Verge once more.”
“First introduced in June, jalapeno is an application specific integrated circuit ASIC made in partnership with Broadcom. It's designed for AI inference, the process of running a trained AI model to complete a task or deploy an agent.”
“Open AI plans to deploy jalapeno in small volumes by the end of this year, but will begin to ramp the volume up into 2027.”