RTX 6000 Ada vs L40S
RTX 6000 Ada starts at $0.75/GPU-hour on-demand; L40S starts at $0.97/GPU-hour on-demand. Compare the exact variants, memory and published specifications below. Peak compute figures do not establish application speed.
RTX 6000 Ada
L40S
Spec sheet
| RTX 6000 Ada | L40S | |
|---|---|---|
| Spec variant | RTX 6000 Ada | L40S |
| Architecture | Ada Lovelace | Ada Lovelace |
| VRAM (spec variant) | 48 GB | 48 GB |
| FP16 TFLOPS (dense) | 364 | 362 |
| Memory bandwidth | 960 GB/s | 864 GB/s |
| TDP | 300 W | 350 W |
| Interconnect | PCIe Gen4 | PCIe Gen4 |
| Launched | 2022 | 2023 |
Rental price per manufacturer-rated FP16 compute: RTX 6000 Ada $2.06 per PFLOP-hour vs L40S $2.68. Formula: cheapest $/hr ÷ dense FP16 PFLOPS (1 PFLOP = 1000 TFLOPS). This uses RTX 6000 Ada and L40S, whose datasheets may differ from the variants above. It is not measured job throughput. Specs: RTX 6000 Ada manufacturer, L40S manufacturer.
What they cost to rent (2026-10-02)
| RTX 6000 Ada | L40S | |
|---|---|---|
| Cheapest on-demand $/hr | $0.75 | $0.97 |
| Cheapest spot/community $/hr | $0.74 | $0.79 |
| Cheapest source | TensorDock | Massed Compute |
| Providers offering it | 6 | 16 |
Lowest recorded on-demand rate per configuration; highlighted = cheaper. Spot/marketplace tiers shown on the individual pages.
FAQ
RTX 6000 Ada is cheaper: the RTX 6000 Ada rents from $0.75 per GPU-hour and the L40S from $0.97 on-demand, updated 2026-10-02.
The largest recorded RTX 6000 Ada variant has 48 GB and the largest L40S variant has 48 GB. Other variants may have less memory. They match on maximum VRAM.
Compare more rental options: the screener · price movers · methodology.