OpenAI reveals 'Jalapeño' chip specs at Hot Chips, comparisons questioned
AccBalanced · x · 2026-08-27
OpenAI revealed the first real specs for its in-house chip 'Jalapeño' at Hot Chips. While some claim it beats Nvidia, analysts note OpenAI compared it against older Nvidia systems (HBM3e-based Blackwell) rather than the contemporary Rubin (which also uses HBM4).
Key metrics:
- Power: Rated 700W, staying under 550W in tests; comparators normalized to 1.2kW (GB200) and 1.4kW (MI355X).
- Performance: Delivered 1.5x-1.9x more work per watt and 1.7x-3.6x lower end-to-end latency.
- Memory: 216 GiB HBM4 per package at 15.4 TB/s.
Critics highlight the lack of controlled, same-generation benchmarks.
More from Infra
- engy.ai processes 50B+ tokens in a day as open-model inference demand surges — const_reborn · 2026-10-16
- New inference engine 'e' hits 10,500 tok/s on a single DGX Station — brandon_galang · 2026-10-16
- SGLang ships Day-0 support for FLUX 3 Image Klein: 10 reference images, BF16/FP8/NVFP4 variants — ying11231 · 2026-10-16
- NVIDIA's Nemotron 3.5 Super VL hits CoreWeave: 12B-active multimodal MoE at $0.25/M input tokens — wandb · 2026-10-16
- Chip equipment beats bull case: 2026 WFE seen at $153B, $278B by 2030 — BenBajarin · 2026-10-16
- Steam now launches in 5.23s, beating Epic's 5.47s — and vLLM gets roasted for slow startup — AlpinDale · 2026-10-16