L40S vs RTX 4090
Datasheet specs side by side, plus what each card actually costs to rent today across every provider we track.
L40S
RTX 4090
Spec sheet
| L40S | RTX 4090 | |
|---|---|---|
| Architecture | Ada Lovelace | Ada Lovelace |
| VRAM (max variant) | 48 GB | 24 GB |
| FP16 TFLOPS (dense) | 362 | 165 |
| Memory bandwidth | 864 GB/s | 1008 GB/s |
| TDP | 350 W | 450 W |
| Interconnect | PCIe Gen4 | PCIe Gen4 |
| Launched | 2023 | 2022 |
Computed price-performance at today's cheapest on-demand rates: L40S $2.43 per PFLOP-hour vs RTX 4090 $2.12. Formula: cheapest $/hr ÷ dense FP16 PFLOPS (1 PFLOP = 1000 TFLOPS). Specs from vendor datasheets (source, source).
What they cost to rent (2026-08-22)
| L40S | RTX 4090 | |
|---|---|---|
| Cheapest on-demand $/hr | $0.88 | $0.35 |
| Cheapest spot/community $/hr | $0.79 | $0.16 |
| Cheapest source | Massed Compute | TensorDock |
| Providers offering it | 16 | 4 |
Cheapest verified on-demand rate per side from today's snapshot; highlighted = cheaper. Spot/marketplace tiers shown on the individual pages.
FAQ
RTX 4090 is cheaper: the L40S rents from $0.88 per GPU-hour and the RTX 4090 from $0.35 on-demand, verified 2026-08-22.
The L40S has 48 GB and the RTX 4090 has 24 GB. The L40S has more.
Prices render from the live dataset each build. More: the screener · price movers · methodology.