Side-by-side GPU comparison: specs, memory, compute performance, and live cloud pricing.
Verdict
K80 has 4 GB more VRAM, making it better suited for large models and long context windows. For compute-bound workloads like training, Radeon Pro V520 delivers 1.2× higher FP16 throughput. K80 supports a broader range of models (486 vs 443 from this catalog), giving more flexibility.
Specifications
| K80 | Radeon Pro V520 | |
|---|---|---|
| VRAM | 12 GB | 8 GB |
| VRAM Type | GDDR5 | HBM2 |
| Memory Bandwidth | 0.2 TB/s | 0.5 TB/s |
| FP16 Performance | 9 TFLOPS | 10 TFLOPS |
| Manufacturer | NVIDIA | AMD |
| 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.
| K80 | Radeon Pro V520 | |
|---|---|---|
| $/hr (cheapest) | $0.18 | — |
| $/TFLOP (compute value) | $0.0206 | — |
| $/GB VRAM (memory value) | $0.0150 | — |
Cloud Pricing
Cheapest on-demand price per provider (single GPU).
K80
| Provider | On-demand | Spot | Rent |
|---|---|---|---|
| Microsoft Azure | $0.18/hr | $0.10/hr |
Radeon Pro V520
No cloud pricing available.
Model Compatibility
Models from the catalog that fit on each GPU, grouped by required precision.
K80 (486 models)
Radeon Pro V520 (443 models)
You might also compare…
Pricing data refreshed hourly · Last updated April 11, 2026 · Browse all comparisons