OpenAI's Jalapeño Chip Beats Nvidia GB200/GB300 in Efficiency
Beth_Kindig · x · 2026-08-30
OpenAI revealed that its in-house Jalapeño chip delivered 1.5X-1.9X higher tokens per watt and 1.7X-3.6X lower latency compared to Nvidia's GB200 and GB300 across GPT-OSS 120B, DeepSeek R1, and Kimi K2.5 1T models. The company is preparing for scale operations and initial deployments before year-end.
Related event: OpenAI's In-House Jalapeño Chip Reportedly Beats Nvidia on Efficiency(3 posts)→
More from Infra
- Perplexity's Portable Computer: A Local-First Agent on Qwen3.8 27B, Near-Zero Cost — 机器之心 · 2026-08-30
- Qwen 350K Context Tested on M5 Max: Performance and Quality — Artistic_Okra7288 · 2026-08-30
- Azure Linux 4.0 Desktop Concept: PowerShell, Edge, and Copilot Pre-installed — unixterminal · 2026-08-30
- Jensen Huang: Built GPU tech first, found endless problems from graphics to molecular dynamics — r0ck3t23 · 2026-08-30
- How to build an LLM inference engine from scratch: 5-layer architecture — glenbeer · 2026-08-30
- Huaqin expects super node revenue to exceed 10B RMB in 2H 2026 — zephyr_z9 · 2026-08-30