Blackwell
NVIDIA B200 180GB
wins
2
The B200 is NVIDIA's Blackwell flagship — 4.5 PFLOPS FP16 and 8 TB/s memory bandwidth make it the most powerful GPU available for AI training at scale.
Blackwell
NVIDIA GB200 NVL72
wins
3
The GB200 NVL72 is NVIDIA's most powerful AI system.
Performance comparison
Visual bars — winner highlighted
NVIDIA B200 180GB
Metric
NVIDIA GB200 NVL72
FP16 TFLOPS
Bandwidth
VRAM
TDP (lower=better)
TFLOPS/watt
GB/s per watt
Full specification table
| Spec | NVIDIA B200 180GB | NVIDIA GB200 NVL72 |
|---|---|---|
| Architecture | Blackwell | Blackwell |
| VRAM | 180 GB HBM3e | 384 GB HBM3e (per GPU) |
| VRAM type | HBM3e | HBM3e (per GPU) |
| Memory bandwidth | 8,000 GB/s | 16,000 GB/s |
| FP16 TFLOPS | 4,500 TFLOPS | 9,000 TFLOPS |
| TDP | 1,000 W | 2,700 W |
| TFLOPS/watt | 4.50 T/W | 3.33 T/W |
| GB/s per watt | 8.00 GB/s/W | 5.93 GB/s/W |
| NVLink | Yes | Yes |
| Release year | 2024 | 2025 |
Live cloud pricing
On-demand $/hr across providers — updated in real time
Power efficiency analysis
TFLOPS/watt and GB/s/watt — critical for data center TCO
NVIDIA B200 180GB
NVIDIA GB200 NVL72
TFLOPS/watt measures compute efficiency — how much AI throughput you get per watt of power consumed. For data centers with PUE of 1.2–1.5, a 10% improvement in TFLOPS/watt translates directly to lower electricity costs and cooling requirements. GB/s/watt measures memory bandwidth efficiency, which is the binding constraint for memory-bound LLM inference workloads.
When to choose each GPU
Choose NVIDIA B200 180GB for:
- Next-gen LLM training
- Trillion-parameter models
- AI factories
Choose NVIDIA GB200 NVL72 for:
- Trillion-parameter training
- AI factory scale
- Next-gen LLM inference
Popular GPU comparisons