A100 vs A40
Datasheet specs side by side, plus what each card actually costs to rent today across every provider we track.
A100
A40
Spec sheet
| A100 | A40 | |
|---|---|---|
| Architecture | Ampere | Ampere |
| VRAM (max variant) | 80 GB | 48 GB |
| FP16 TFLOPS (dense) | 312 | 150 |
| Memory bandwidth | 1935 GB/s | 696 GB/s |
| TDP | 300 W | 300 W |
| Interconnect | PCIe Gen4 | NVLink 112.5GB/s |
| Launched | 2020 | 2020 |
Computed price-performance at today's cheapest on-demand rates: A100 $2.85 per PFLOP-hour vs A40 $2.93. Formula: cheapest $/hr ÷ dense FP16 PFLOPS (1 PFLOP = 1000 TFLOPS). Specs from vendor datasheets (source, source).
What they cost to rent (2026-07-18)
| A100 | A40 | |
|---|---|---|
| Cheapest on-demand $/hr | $0.89 | $0.44 |
| Cheapest spot/community $/hr | $0.68 | $0.35 |
| Cheapest source | Jarvislabs | RunPod |
| Providers offering it | 16 | 2 |
Cheapest verified on-demand rate per side from today's snapshot; highlighted = cheaper. Spot/marketplace tiers shown on the individual pages.
FAQ
Is the A100 cheaper to rent than the A40?
A40 is cheaper: the A100 rents from $0.89 per GPU-hour and the A40 from $0.44 on-demand, verified 2026-07-18.
Which has more VRAM, A100 or A40?
The A100 has 80 GB and the A40 has 48 GB. The A100 has more.
Prices render from the live dataset each build. More: the screener · price movers · methodology.