Comparison · GPU vs GPU · read 00:32 UTCL40S vs A100 80GB
Specifications, today's prices from 123 providers, price per unit of memory and compute, and who rents each cheapest. Better values are highlighted; lower is better for prices.
Side by sideSpecs, prices, value
Highlighted cells are the better of the two: more memory and compute, lower prices, lower cost per unit.
| L40S | A100 80GB | Difference | |
|---|---|---|---|
| Memory & compute | |||
| VRAM | 48 GB | 80 GB | -40% |
| Memory bandwidth | 0.86 TB/s | 2.00 TB/s | -57% |
| FP16 tensor | 362 TFLOPS | 312 TFLOPS | +16% |
| FP32 | 91.6 TFLOPS | 19.5 TFLOPS | +370% |
| Power | 350 W | 400 W | -13% |
| Prices today | |||
| Cheapest on-demand | $0.38 | $0.60 | -37% |
| Median on-demand | $1.24 | $1.92 | -36% |
| Highest on-demand | $3.51 | $5.29 | -34% |
| Cheapest spot | $0.33 | $0.57 | -42% |
| Cheapest reserved | $0.44 | $0.76 | -42% |
| Current offers (n) | 140 | 188 | -26% |
| Providers with a fresh offer | 54 | 69 | -22% |
| Value | |||
| Per GB of VRAM · hour (cheapest) | $0.008 | $0.008 | +5% |
| Per GB of VRAM · hour (median) | $0.026 | $0.024 | +7% |
| Per PFLOP FP16 · hour (median) | $3.412 | $6.139 | -44% |
| Per TB/s · hour (median) | $1.430 | $0.958 | +49% |
| Trend | |||
| 30-day median change | +12.6% | -3.5% | — |
| 90-day median change | +22.1% | -0.7% | — |
90 days · median on-demand price · rebased to 100How the two have moved
Both medians indexed to 100 ninety days ago, so the slopes compare even though the price levels differ.
Cheapest providers today · on-demand · current offersWho rents each one cheapest
- 1
LiumTrust 402× $0.38 - 2
Clore.aiTrust 461× $0.50 - 3
GPUBankTrust 931× $0.55
- 1
Vast.aiTrust 784× $0.60 - 2
packet.ai1× $0.89 - 3GPUBankTrust 931× $0.95
Verdict · computed from the numbers aboveChoose one, choose the other
Choose the L40S if…
- the hourly price matters most: median $1.24 against $1.92, 36% less.
Choose the A100 80GB if…
- your model needs more than 48 GB per GPU: 80 GB against 48 GB.
- you serve LLMs: memory bandwidth per dollar is better ($0.958 per TB/s-hour against $1.430).
- you want choice: 69 providers have a fresh offer today against 54.
Questions about L40S vs A100 80GB
Which is cheaper to rent, the L40S or the A100 80GB?
Today the cheapest current on-demand L40S is $0.38 per GPU-hour and the cheapest A100 80GB is $0.60; medians are $1.24 and $1.92. Cheapest excludes offers marked unavailable and counts one floor per marketplace.
How much memory do the L40S and A100 80GB have?
48 GB of memory on the L40S, 80 GB of HBM2e on the A100 80GB, at 0.86 and 2.00 TB/s.
Where do these numbers come from?
From 328 current offers read on the providers' own pages and APIs over the last 45 days (reference 00:32 UTC), or in our October 2026 market study for the few providers our collector does not read. Specifications come from manufacturer datasheets. Every price on the GPU pages links to its receipt and shows its read date.