Side-by-side GPU comparison: specs, memory, compute performance, and live cloud pricing.
Verdict
DGX Spark (GB10) has 34 GB more VRAM, making it better suited for large models and long context windows. For compute-bound workloads like training, H100 NVL delivers 6.7× higher FP16 throughput. DGX Spark (GB10) supports a broader range of models (649 vs 637 from this catalog), giving more flexibility.
Specifications
| DGX Spark (GB10) | H100 NVL | |
|---|---|---|
| VRAM | 128 GB | 94 GB |
| VRAM Type | LPDDR5X | HBM3 |
| Memory Bandwidth | 0.3 TB/s | 3.9 TB/s |
| FP16 Performance | 125 TFLOPS | 835 TFLOPS |
| Manufacturer | NVIDIA | NVIDIA |
| FP8 Support | Yes | Yes |
| FP4 Support | Yes | No |
Price / Performance
Based on cheapest single-GPU on-demand pricing. Lower $/TFLOP = better compute value; lower $/GB = better memory value.
| DGX Spark (GB10) | H100 NVL | |
|---|---|---|
| $/hr (cheapest) | — | $1.80 |
| $/TFLOP (compute value) | — | $0.0022 |
| $/GB VRAM (memory value) | — | $0.0191 |
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.
DGX Spark (GB10) (649 models)
H100 NVL (637 models)
You might also compare…
Pricing data refreshed hourly · Last updated April 11, 2026 · Browse all comparisons