Side-by-side GPU comparison: specs, memory, compute performance, and live cloud pricing.
Verdict
A10G has 8 GB more VRAM, making it better suited for large models and long context windows. For compute-bound workloads like training, A10G delivers 1.3× higher FP16 throughput. At $0.18/hr vs $1.01/hr, V100 is the more cost-efficient choice for inference. A10G supports a broader range of models (566 vs 502 from this catalog), giving more flexibility.
Specifications
| A10G | V100 | |
|---|---|---|
| VRAM | 24 GB | 16 GB |
| VRAM Type | GDDR6 | HBM2 |
| Memory Bandwidth | 0.6 TB/s | 0.9 TB/s |
| FP16 Performance | 36 TFLOPS | 28 TFLOPS |
| Manufacturer | NVIDIA | NVIDIA |
| FP8 Support | No | No |
| FP4 Support | No | No |
Price / Performance
Based on cheapest single-GPU on-demand pricing. Lower $/TFLOP = better compute value; lower $/GB = better memory value.
| A10G | V100 | |
|---|---|---|
| $/hr (cheapest) | $1.01 | $0.18✓ best |
| $/TFLOP (compute value) | $0.0283 | $0.0064✓ best |
| $/GB VRAM (memory value) | $0.0419 | $0.0112✓ 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.
A10G (566 models)
V100 (502 models)
You might also compare…
Pricing data refreshed hourly · Last updated April 11, 2026 · Browse all comparisons