AITechRadarabout 2 hours ago
OpenAI Jalapeño chip benchmarks target Nvidia GB300
5 min read
OpenAI published first Jalapeño benchmarks at Hot Chips, claiming 1.5 to 1.9x more throughput per kilowatt and up to 3.6x lower latency than Nvidia's GB200 and GB300 rack systems. Nvidia's GB300 still leads absolute throughput per package by 20-25 percent. Volume production ramps in 2027.
Level
Hype check
Tap to vote and see what everyone thinks.
Summary by ByteBrief
