Side-by-side GPU comparison: specs, memory, compute performance, and live cloud pricing.
Verdict
GH200 has 2 GB more VRAM, making it better suited for large models and long context windows. For compute-bound workloads like training, GH200 delivers 1.2× higher FP16 throughput. At $1.80/hr vs $2.29/hr, H100 NVL is the more cost-efficient choice for inference.
Specifications
| GH200 | H100 NVL | |
|---|---|---|
| VRAM | 96 GB | 94 GB |
| VRAM Type | HBM3 | HBM3 |
| Memory Bandwidth | 4.0 TB/s | 3.9 TB/s |
| FP16 Performance | 990 TFLOPS | 835 TFLOPS |
| Manufacturer | NVIDIA | NVIDIA |
| FP8 Support | Yes | Yes |
| FP4 Support | No | No |
Price / Performance
Based on cheapest single-GPU on-demand pricing. Lower $/TFLOP = better compute value; lower $/GB = better memory value.
| GH200 | H100 NVL | |
|---|---|---|
| $/hr (cheapest) | $2.29 | $1.80✓ best |
| $/TFLOP (compute value) | $0.0023 | $0.0022✓ best |
| $/GB VRAM (memory value) | $0.0239 | $0.0191✓ best |
Cloud Pricing
Cheapest on-demand price per provider (single GPU).
Model Compatibility
Models from the catalog that fit on each GPU, grouped by required precision.
GH200 (637 models)
H100 NVL (637 models)
You might also compare…
Pricing data refreshed hourly · Last updated April 11, 2026 · Browse all comparisons