Hopper
NVIDIA H100 NVL
wins
4
The H100 NVL is a PCIe form-factor Hopper GPU with 94GB HBM3 and NVLink support.
Hopper
NVIDIA H200 141GB
wins
2
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.
Performance comparison
Visual bars — winner highlighted
NVIDIA H100 NVL
Metric
NVIDIA H200 141GB
FP16 TFLOPS
Bandwidth
VRAM
TDP (lower=better)
TFLOPS/watt
GB/s per watt
TFLOPS/$
FP16 TFLOPS ÷ best on-demand $/hr
GB/s per $
Memory bandwidth ÷ best on-demand $/hr
Full specification table
| Spec | NVIDIA H100 NVL | NVIDIA H200 141GB |
|---|---|---|
| Architecture | Hopper | Hopper |
| VRAM | 94 GB HBM3 | 141 GB HBM3e |
| VRAM type | HBM3 | HBM3e |
| Memory bandwidth | 3,938 GB/s | 4,800 GB/s |
| FP16 TFLOPS | 1,979 TFLOPS | 989 TFLOPS |
| TDP | 400 W | 700 W |
| TFLOPS/watt | 4.95 T/W | 1.41 T/W |
| GB/s per watt | 9.85 GB/s/W | 6.86 GB/s/W |
| NVLink | Yes | Yes |
| Release year | 2023 | 2024 |
| Best cloud price | $3.29/hr | $2.61/hr |
| TFLOPS/$ | 601.5 | 378.9 |
| GB/s per $ | 1197 | 1839 |
Live cloud pricing
On-demand pricing across providers — updated in real time
NVIDIA H100 NVL
NVIDIA H200 141GB
Power efficiency analysis
TFLOPS/watt and GB/s/watt — critical for data center TCO
NVIDIA H100 NVL
NVIDIA H200 141GB
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.
Performance-per-dollar
TFLOPS/$ and GB/s/$ at current best cloud prices
NVIDIA H100 NVL
NVIDIA H200 141GB
TFLOPS/$ = FP16 TFLOPS ÷ best on-demand $/hr. Higher is better — more compute per dollar. GB/s/$ = memory bandwidth ÷ best on-demand $/hr. For memory-bound inference workloads (most LLM serving), GB/s/$ is often a better predictor of cost-efficiency than TFLOPS/$. Prices are live from the Compute Comparison API and update in real time.
Workload Cost Comparison
Total job cost = best on-demand $/hr × GPU count × hours
NVIDIA H100 NVL costs 1.3× more at current best prices. 2.0× the FP16 compute (1979 vs 989 TFLOPS) supports faster training and higher batch throughput.
| Workload | Scale | NVIDIA H100 NVL | NVIDIA H200 141GB |
|---|---|---|---|
| 7B LLM fine-tune | 8× GPU, 24 h | $632 | $501▼ |
| 70B LLM fine-tune | 64× GPU, 72 h | $15k | $12k▼ |
| Inference server | 1× GPU, 730 h | $2.4k | $1.9k▼ |
| Image gen batch | 4× GPU, 8 h | $105 | $84▼ |
Based on current best on-demand prices. Spot pricing typically 40–70% lower. Actual cost depends on provider, region, and availability.
When to choose each GPU
Choose NVIDIA H100 NVL for:
- LLM inference
- PCIe server deployments
- Dual-GPU NVLink pairs
Weaknesses / Limitations
- Lower FP16 TFLOPS (1,979 per dual-GPU) than SXM5 per-card
- Requires paired NVLink configuration — not a single-card solution
- Limited availability compared to standard H100 SXM
Choose NVIDIA H200 141GB for:
- Very large LLMs
- Memory-bound inference
- Multi-modal models
Weaknesses / Limitations
- Very limited cloud availability — fewer providers than H100
- Premium pricing over H100 with same FP16 TFLOPS
- 700W TDP — same power envelope as H100 with no efficiency gain
Popular GPU comparisons