# OpenAI reports first Jalapeño accelerator benchmarks

_Published Friday, August 28, 2026 at 9:18 AM EDT · Infrastructure · Latest · Tier 2 — Notable_

OpenAI reported first benchmark results for its Jalapeño AI accelerator at a media briefing, saying the chip delivered 1.5 to 1.9 times more AI work per watt at peak throughput and 1.7 to 3.6 times lower end-to-end latency than comparable systems listed on InferenceX.

The company said the tests used single-token prediction without speculative decoding. Jalapeño is designed around close memory and compute affinity to reduce data movement. OpenAI plans small-volume rollouts at year-end and a larger ramp in 2027.

## Sources

- [EE Times](https://www.eetimes.com/first-benchmarks-revealed-for-jalapeno-openais-clean-sheet-general-purpose-ai-accelerator-asic/)

---
Canonical: https://techandbusiness.org/newswire/PPMCIskjDwdVuT8dXKoSq6
Published: 2026-08-28T13:18:47.590Z
Story chronology: 2026-08-27T22:14:16.000Z
Retrieved: 2026-10-12T16:43:16.512Z
Publisher: Tech & Business (techandbusiness.org)