L40S vs Tesla V100
L40S starts at $0.97/GPU-hour on-demand; Tesla V100 starts at $0.17/GPU-hour on-demand. Compare the exact variants, memory and published specifications below. Peak compute figures do not establish application speed.
L40S
Tesla V100
Spec sheet
| L40S | Tesla V100 | |
|---|---|---|
| Spec variant | L40S | Tesla V100 (unspecified) |
| Architecture | Ada Lovelace | Volta |
| VRAM (spec variant) | 48 GB | 16 GB |
| FP16 TFLOPS (dense) | 362 | 125 |
| Memory bandwidth | 864 GB/s | 900 GB/s |
| TDP | 350 W | 300 W |
| Interconnect | PCIe Gen4 | NVLink 300GB/s |
| Launched | 2023 | 2017 |
What they cost to rent (2026-10-02)
| L40S | Tesla V100 | |
|---|---|---|
| Cheapest on-demand $/hr | $0.97 | $0.17 |
| Cheapest spot/community $/hr | $0.79 | $0.19 |
| Cheapest source | Massed Compute | TensorDock |
| Providers offering it | 16 | 6 |
Lowest recorded on-demand rate per configuration; highlighted = cheaper. Spot/marketplace tiers shown on the individual pages.
FAQ
Is the L40S cheaper to rent than the Tesla V100?
Tesla V100 is cheaper: the L40S rents from $0.97 per GPU-hour and the Tesla V100 from $0.17 on-demand, updated 2026-10-02.
Which has more VRAM, L40S or Tesla V100?
The largest recorded L40S variant has 48 GB and the largest Tesla V100 variant has 16 GB. Other variants may have less memory. The L40S has more.
Compare more rental options: the screener · price movers · methodology.