Side-by-side GPU comparison: specs, memory, compute performance, and live cloud pricing.
Verdict
L40S has 8 GB more VRAM, making it better suited for large models and long context windows. For compute-bound workloads like training, L40S delivers 1.2× higher FP16 throughput. At $0.60/hr vs $0.93/hr, L40S is the more cost-efficient choice for inference. L40S supports a broader range of models (624 vs 612 from this catalog), giving more flexibility.
Specifications
| A100 40GB | L40S | |
|---|---|---|
| VRAM | 40 GB | 48 GB |
| VRAM Type | HBM2 | GDDR6 |
| Memory Bandwidth | 1.6 TB/s | 0.9 TB/s |
| FP16 Performance | 312 TFLOPS | 366 TFLOPS |
| Manufacturer | NVIDIA | NVIDIA |
| FP8 Support | No | 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.
| A100 40GB | L40S | |
|---|---|---|
| $/hr (cheapest) | $0.93 | $0.60✓ best |
| $/TFLOP (compute value) | $0.0030 | $0.0016✓ best |
| $/GB VRAM (memory value) | $0.0232 | $0.0125✓ 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.
A100 40GB (612 models)
L40S (624 models)
You might also compare…
Pricing data refreshed hourly · Last updated April 11, 2026 · Browse all comparisons