Hopper
NVIDIA H200 141GB
wins
1
The H200 upgrades the H100 with 141GB HBM3e memory and 4.8 TB/s bandwidth — a massive boost for memory-bound workloads like large LLM inference.
Blackwell
NVIDIA B200 180GB
wins
4
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.
Performance comparison
Visual bars — winner highlighted
NVIDIA H200 141GB
Metric
NVIDIA B200 180GB
FP16 TFLOPS
Bandwidth
VRAM
TDP (lower=better)
TFLOPS/watt
GB/s per watt
Full specification table
| Spec | NVIDIA H200 141GB | NVIDIA B200 180GB |
|---|---|---|
| Architecture | Hopper | Blackwell |
| VRAM | 141 GB HBM3e | 180 GB HBM3e |
| VRAM type | HBM3e | HBM3e |
| Memory bandwidth | 4,800 GB/s | 8,000 GB/s |
| FP16 TFLOPS | 989 TFLOPS | 4,500 TFLOPS |
| TDP | 700 W | 1,000 W |
| TFLOPS/watt | 1.41 T/W | 4.50 T/W |
| GB/s per watt | 6.86 GB/s/W | 8.00 GB/s/W |
| NVLink | Yes | Yes |
| Release year | 2024 | 2024 |
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 H200 141GB
NVIDIA B200 180GB
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 H200 141GB for:
- Very large LLMs
- Memory-bound inference
- Multi-modal models
Choose NVIDIA B200 180GB for:
- Next-gen LLM training
- Trillion-parameter models
- AI factories
Popular GPU comparisons