Side-by-side GPU comparison: specs, memory, compute performance, and live cloud pricing.
Verdict
For compute-bound workloads like training, M60 delivers 1.7× higher FP16 throughput. At $0.23/hr vs $0.60/hr, M60 is the more cost-efficient choice for inference.
Specifications
| M60 | P4 | |
|---|---|---|
| VRAM | 8 GB | 8 GB |
| VRAM Type | GDDR5 | GDDR5 |
| Memory Bandwidth | 0.2 TB/s | 0.2 TB/s |
| FP16 Performance | 10 TFLOPS | 6 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.
| M60 | P4 | |
|---|---|---|
| $/hr (cheapest) | $0.23✓ best | $0.60 |
| $/TFLOP (compute value) | $0.0238✓ best | $0.1091 |
| $/GB VRAM (memory value) | $0.0285✓ best | $0.0750 |
Cloud Pricing
Cheapest on-demand price per provider (single GPU).
M60
| Provider | On-demand | Spot | Rent |
|---|---|---|---|
| Microsoft Azure | $0.23/hr | $0.13/hr |
P4
| Provider | On-demand | Spot | Rent |
|---|---|---|---|
| Google Cloud | $0.60/hr | $0.06/hr |
Model Compatibility
Models from the catalog that fit on each GPU, grouped by required precision.
M60 (443 models)
P4 (443 models)
You might also compare…
Pricing data refreshed hourly · Last updated April 11, 2026 · Browse all comparisons