GPU comparison
V100 SXM2 16GB vs L40S 48GB: specs and rental cost comparison
Direct answer
V100 SXM2 16GB vs L40S 48GB: V100 SXM2 16GB is cheaper on the lowest tracked rental row at $0.17 per GPU-hour, versus $0.60 for L40S 48GB. That makes L40S 48GB about 243% more expensive per GPU-hour on the cheapest rows in the ByteCosts GPU catalog. V100 SXM2 16GB has 16 GB VRAM and L40S 48GB has 48 GB VRAM. The tables compare source-backed specs and value metrics only where both GPUs have a real spec field and a tracked rental rate. Rental prices are list rates per GPU-hour, before committed-use discounts, capacity limits, or region constraints.
Compare GPU rental across providers - Cheapest per-GPU-hour by accelerator →
V100 SXM2 16GB vs L40S 48GB: rental value
Cheapest tracked on-demand rental rows and normalized value metrics.
| Metric | V100 SXM2 16GB | L40S 48GB |
|---|---|---|
| Cheapest rental / GPU-hour | $0.17 | $0.60 |
| $ / GB VRAM | $0.011 | $0.012 |
| $ / FP16 TFLOP-hour | $0.0014 | $0.0017 |
V100 SXM2 16GB vs L40S 48GB: specs
Hardware specs from the committed GPU spec catalog. Rows with missing source fields on either GPU are omitted.
| Spec | V100 SXM2 16GB | L40S 48GB |
|---|---|---|
| Architecture | volta | ada |
| VRAM | 16 GB | 48 GB |
| Memory bandwidth | 900 GB/s | 864 GB/s |
| FP16 tensor compute | 125.0 TFLOPS | 362.1 TFLOPS |
| TDP | 300 W | 350 W |
Cheapest tracked rental rows
| GPU | Provider | Instance | Region | GPUs | Instance/hr | Per-GPU/hr |
|---|---|---|---|---|---|---|
| V100 SXM2 16GB | Vast.ai | 2x-Tesla_V100-32-65536 | North Carolina, US, NA | 2 | $0.35 | $0.17 |
| L40S 48GB | Vast.ai | 1x-L40S-32-65536 | Japan, JP, AS | 1 | $0.60 | $0.60 |
Frequently asked questions
Is V100 SXM2 16GB or L40S 48GB cheaper to rent?
V100 SXM2 16GB is cheaper on the lowest tracked row at $0.17 per GPU-hour, compared with $0.60 for L40S 48GB. Region, capacity, spot interruption, and discounts can change a production bill.
Which is better value, V100 SXM2 16GB or L40S 48GB?
Use the value table above: $/GB-VRAM is always shown from real VRAM and rental rate, while $/TFLOP rows are shown only when both GPUs have the relevant sourced compute spec. Do not compare a missing field as zero.
Where do these GPU comparison numbers come from?
Rental rates come from the ByteCosts GPU rental catalog normalized from the SkyPilot catalog. Hardware specs come from the committed GPU spec catalog and its per-GPU source URLs.
Cite this page
V100 SXM2 16GB vs L40S 48GB GPU comparison. ByteCosts. Updated June 15, 2026. https://bytecosts.com/gpu/compare/v100-sxm2-16gb-vs-l40s-48gb/