Flopper.io System Specification Sheet
October 4, 2026
flopper.io/system/nvidia-dgx-b300NVIDIA DGX B300
8x B300 Blackwell Ultra rack 2025
Overview
36,000
FP8 TFLOPS Dense
2.1 TB
Aggregate Memory
64.0 TB/s
Aggregate Bandwidth
14.0 kW
Aggregate Power
Performance Metrics
| Precision | Peak (TFLOPS) | Per GPU (TFLOPS) | TFLOPS/W |
|---|---|---|---|
| FP64 | 10 | 1.3 | — |
| FP32 | 600 | 75 | — |
| TF32 | 9,000 | 1,125 | — |
| FP16 | 18,000 | 2,250 | — |
| BF16 | 18,000 | 2,250 | — |
| FP8 | 36,000 | 4,500 | — |
| FP4 | 108,000 | 13,500 | — |
| FP6 | 36,000 | 4,500 | — |
All figures are dense. Vendors commonly headline the sparse number, which is twice the dense one.
Configuration
- Accelerator
- B300 SXM 262GB
- Count
- 8
- Memory per GPU
- 263 GB
- Bandwidth per GPU
- 8.0 TB/s
Power & Efficiency
- Aggregate Power
- 14.0 kW
- TDP per GPU
- 1400 W
- FP8 Efficiency
- 2.57 TFLOPS/W
- Aggregate Bandwidth
- 64.0 TB/s
System Details
Vendor: NVIDIA
Family: DGX
Architecture: Blackwell Ultra
Form Factor: rack
Release Year: 2025
Process Node: 4nm
Interconnect
NVSwitch + NVLink
Notes
Eight Blackwell Ultra SXM GPUs on the HGX B300 baseboard with Intel Xeon 6776P processors, in a 10U chassis. NVIDIA quotes 144 PFLOPS of FP4 inference performance for this machine, which is the sparse figure; the dense equivalent is 108 PFLOPS, and both are recorded. Power is given by NVIDIA as approximately 14 kW.