OpenAI's Gen 1 Chip Challenges Nvidia Vera Rubin in Inference Efficiency
haider1 · x · 2026-08-26
SemiAnalysis' InferenceX benchmarks reveal that OpenAI's first-generation chip, "Jalapeño," delivers impressive inference performance, challenging Nvidia's upcoming Vera Rubin.
Benchmark Highlights
- DeepSeek R1: Jalapeño achieves 1.7x better performance-per-watt and 3.6x lower latency than Rubin, significantly outperforming GB200.
- GPT-OSS: 1.9x better performance-per-watt and 1.7x lower latency.
- Kimi K2.5: 1.5x better performance-per-watt and 3.4x lower latency.
First-generation chips are rarely competitive, but OpenAI's entry beats Nvidia Blackwell and rivals the next-gen Rubin in key metrics.
More from Infra
- OpenAI's Jalapeño Chip Leak: Potential 50x Speed Boost for GPT — Yuchenj_UW · 2026-08-26
- Open Source vs Labs: Startups Must Build the Full Stack — matt_slotnick · 2026-08-26
- Next AI hardware race might be about inference speed — Delicious-Flan88 · 2026-08-26
- NVIDIA Releases Get Started Guide for Open Model Routing — NVIDIAAI · 2026-08-26
- Nvidia's dominance in both inference and training challenged; will specialized chips eventually win? — ivan_bezdomny · 2026-08-26
- AC2 launches private beta: Build a model factory to train, serve, and improve models — ypatil125 · 2026-08-26