A40 vs L40
A40 starts at $0.49/GPU-hour on-demand; L40 starts at $0.79/GPU-hour on-demand. Compare the exact variants, memory and published specifications below. Peak compute figures do not establish application speed.
A40
L40
Spec sheet
| A40 | L40 | |
|---|---|---|
| Spec variant | A40 | L40 |
| Architecture | Ampere | Ada Lovelace |
| VRAM (spec variant) | 48 GB | 48 GB |
| FP16 TFLOPS (dense) | 150 | 181 |
| Memory bandwidth | 696 GB/s | 864 GB/s |
| TDP | 300 W | 300 W |
| Interconnect | NVLink 112.5GB/s | PCIe Gen4 |
| Launched | 2020 | 2022 |
Rental price per manufacturer-rated FP16 compute: A40 $3.27 per PFLOP-hour vs L40 $4.36. Formula: cheapest $/hr ÷ dense FP16 PFLOPS (1 PFLOP = 1000 TFLOPS). This uses A40 and L40, whose datasheets may differ from the variants above. It is not measured job throughput. Specs: A40 manufacturer, L40 manufacturer.
What they cost to rent (2026-10-02)
| A40 | L40 | |
|---|---|---|
| Cheapest on-demand $/hr | $0.49 | $0.79 |
| Cheapest spot/community $/hr | – | $0.69 |
| Cheapest source | RunPod | Thunder Compute |
| Providers offering it | 2 | 6 |
Lowest recorded on-demand rate per configuration; highlighted = cheaper. Spot/marketplace tiers shown on the individual pages.
FAQ
A40 is cheaper: the A40 rents from $0.49 per GPU-hour and the L40 from $0.79 on-demand, updated 2026-10-02.
The largest recorded A40 variant has 48 GB and the largest L40 variant has 48 GB. Other variants may have less memory. They match on maximum VRAM.
Compare more rental options: the screener · price movers · methodology.