OpenAI’s 700W Jalapeño ASIC outpaces 1,400W Nvidia flagship GPU — claims up to 1.9x throughput per kilowatt and 3.6x lower latency, co-developed with Broadcom
OpenAI Jalapeño ASIC claims 1.9x throughput per watt over Nvidia GPU.
“OpenAI’s 700W Jalapeño ASIC outpaces 1,400W Nvidia flagship GPU — claims up to 1.9x throughput per kilowatt and 3.6x lower latency, co-developed with Broadcom Tom's…”
Why it matters
Weekly Silicon's editorial model scored this 5.00/10 overall, reading it above all as a hardware story — products that turn silicon roadmaps into things you can deploy. Its strongest dimension is technology breakthrough at 7/10 — a genuine capability or engineering advance rather than a routine product update — with economic impact close behind at 6/10, pointing to meaningful consequences for capital, capacity, or competition across the industry. The effects land first in the CA / Silicon Valley region, so readers there should watch for follow-on announcements.
Derived from the AI score breakdown below.
AI score breakdown
A composite of 5.00/10 put this story at #1 for Wednesday, August 26, 2026, driven mostly by technology breakthrough (7/10) and economic impact (6/10).
Composite is the weighted sum of the five dimensions. How scoring works →
Related stories
- OpenAI’s Jalapeño AI chip brings new 'threat' to Nvidia margins as custom silicon gains ground · 2026-08-27
- Hot Chips 2026: CUDA Targets RISC-V – By Chester Lam · 2026-08-25
- Apple’s new M6 chip gets more cores and more AI compute · 2026-08-25
- Anthropic hires Google chip veteran Amir Salek as part of push into hardware · 2026-08-23
- Geekbench 6.7 - Geekbench Blog · 2026-04-09