Flopper.io GPU Specification Sheet
October 20, 2026
flopper.io/gpu/openai-jalapenoOpenAI Jalapeño
Jalapeño Custom 2026
Overview
—
FP32 TFLOPS
216 GB
Memory HBM4
15.4 TB/s
Memory Bandwidth
700 W
TDP
Performance Metrics
| Precision | Peak (dense) | Bits | Type |
|---|---|---|---|
| FP64 | — | — | Standard |
| FP32 | — | — | Standard |
| TF32 | — | — | Standard |
| BF16 | — | 16 | Standard |
| FP16 | — | — | Standard |
| FP8 | 3400.0 | 8 | Standard |
| FP6 | — | — | Standard |
| FP4 | 13400.0 | 4 | Standard |
| INT8 | — | — | Standard |
Memory Specifications
- Capacity
- 216 GB
- Type
- HBM4
- Bandwidth
- 15.4 TB/s
- Interface Width
- —
Power & Efficiency
- TDP
- 700 W
- Max power (Flopper estimate)
- ~805 W est.
- FP32 dense TFLOPS per W of TDP
- —
- FP16 dense TFLOPS per W of TDP
- —
Flopper estimate: 700 W TDP x 1.15. The vendor publishes no maximum board power for this part. Per W of TDP figures divide dense peak by accelerator TDP. Board power only: excludes host CPUs, networking, cooling and facility overhead.
Hardware Details
Vendor: OpenAI
Architecture: Jalapeño
Process Node: —
Form Factor: Custom
Launch Year: 2026
Interconnect
GPU-to-GPU: Ethernet scale-up (Broadcom Tomahawk 6)
Bandwidth: 600 GB/s direction and scope not stated by vendor
Chip Design
Chiplets: 2 (1 compute die + 1 IO chiplet)