RTX 4090 vs A100
RTX 4090 starts at $0.35/GPU-hour on-demand; A100 starts at $0.89/GPU-hour on-demand. Compare the exact variants, memory and published specifications below. Peak compute figures do not establish application speed.
60.7% cheaper at RTX 4090.
updated 2026-10-06. Price alone does not establish equivalent capacity or performance.
RTX 4090
A100
Spec sheet
| RTX 4090 | A100 | |
|---|---|---|
| Spec variant | RTX 4090 | A100 SXM 40GB |
| Architecture | Ada Lovelace | Ampere |
| VRAM (spec variant) | 24 GB | 40 GB |
| FP16 TFLOPS (dense) | 165 | 312 |
| Memory bandwidth | 1008 GB/s | 1555 GB/s |
| TDP | 450 W | 400 W |
| Interconnect | PCIe Gen4 | NVLink 600GB/s |
| Launched | 2022 | 2020 |
Rental price per manufacturer-rated FP16 compute: RTX 4090 $2.12 per PFLOP-hour vs A100 $2.85. Formula: cheapest $/hr ÷ dense FP16 PFLOPS (1 PFLOP = 1000 TFLOPS). This uses RTX 4090 and A100 SXM 40GB, whose datasheets may differ from the variants above. It is not measured job throughput. Specs: RTX 4090 manufacturer, A100 manufacturer.
What they cost to rent (2026-10-06)
| RTX 4090 | A100 | |
|---|---|---|
| Cheapest on-demand $/hr | $0.35 | $0.89 |
| Cheapest spot/community $/hr | $0.16 | $0.679 |
| Cheapest source | TensorDock | Jarvislabs |
| Providers offering it | 5 | 22 |
Lowest recorded on-demand rate per configuration; highlighted = cheaper. Spot/marketplace tiers shown on the individual pages.
FAQ
RTX 4090 is cheaper: the RTX 4090 rents from $0.35 per GPU-hour and the A100 from $0.89 on-demand, updated 2026-10-06.
The largest recorded RTX 4090 variant has 24 GB and the largest A100 variant has 80 GB. Other variants may have less memory. The A100 has more.
Compare more rental options: the screener · price movers · methodology.