OpenAI unveils Jalapeño, a Broadcom-built 700W inference ASIC that beats Nvidia Blackwell on tokens-per-watt
OpenAI
On Aug 25, 2026, OpenAI revealed Jalapeño, its first-generation inference-optimized custom ASIC co-developed with Broadcom and fabricated by TSMC on N3P (compute die) / N3E (I/O chiplet), with HBM4 memory. Per-chip: 13.4 petaFLOPS at MXFP4, 216 GB HBM4 across six 12-high stacks, 15.4 TB/s memory bandwidth, 700W TDP. Rack: 128 accelerators, 1.7 exaFLOPS of 4-bit compute, 27.5 TB HBM4, ~2 PB/s memory bandwidth. On SemiAnalysis InferenceX it shows 1.5x-1.9x throughput and 1.7x-3.6x lower latency than competing GB200/GB300 systems, with 2.1x-4.1x advantage on ultra-low-latency workloads.
Why it matters
OpenAI's first custom inference silicon and the most credible public threat to Nvidia's CUDA moat in inference; suggests vertical-integration economics are now within reach for top labs.
Importance: 5/5
first custom inference ASIC from OpenAI; beats Nvidia Blackwell on tokens/watt