GPU comparison
L4 vs A100: specs and rental prices
NVIDIA L4 against NVIDIA A100: 24 GB against 80 GB of memory, lowest listed on-demand price $0.80 against $1.35 per GPU-hour. Specs from NVIDIA, prices as of Oct 25, 2026.
In short
- The A100 lists 80 GB of GPU memory against 24 GB for the L4: 3.33× higher.
- The A100 lists 2,039 GB/s of memory bandwidth against 300 GB/s for the L4: 6.8× higher.
- The A100 lists 624 TFLOPS of FP16 / BF16 tensor throughput against 242 TFLOPS for the L4: 2.58× higher.
- Maximum power is listed at 72 W for the L4 and 400 W for the A100.
- Not every figure can be compared: at least one vendor page does not publish: FP8 tensor throughput; FP64 throughput; GPU-to-GPU interconnect.
- The lowest listed on-demand price is $0.80 per GPU-hour for the L4 (AWS) and $1.35 for the A100 (Hyperstack).
- Per GB of GPU memory that is $0.034 per hour for the L4 and $0.017 for the A100.
This summary is generated from the tables below. Prices were last checked Oct 25, 2026. A listing not re-checked for 7 days is greyed and left out of every lowest-price figure; after 14 days it is removed from the page.
Specifications side by side
| Specification | L4 | A100 80GB SXM | Difference |
|---|---|---|---|
| GPU memory | 24 GB | 80 GB | A100 3.33× higher |
| Memory type | Not published | HBM2e | — |
| Memory bandwidth | 300 GB/s | 2,039 GB/s | A100 6.8× higher |
| FP8 tensor throughput | 485 TFLOPS (with sparsity) | Not published | — |
| FP16 / BF16 tensor throughput, with sparsity | 242 TFLOPS | 624 TFLOPS | A100 2.58× higher |
| TF32 tensor throughput, with sparsity | 120 TFLOPS | 312 TFLOPS | A100 2.6× higher |
| FP64 throughput | Not published | 9.7 TFLOPS | — |
| Maximum power | 72 W | 400 W | A100 5.56× higher |
| GPU-to-GPU interconnect | Not published | 600 GB/s | — |
Compared versions: L4 and A100 80GB SXM. The figure in the stronger cell is shaded; power is shown without a winner. Two throughput figures are compared only when both vendors state them on the same basis (both with sparsity, or both dense), and “derived” means a total the vendor publishes divided by the GPU count it publishes. Full tables with sources: L4 specifications · A100 specifications.
Rental prices
| Rental price | L4 | A100 | Difference |
|---|---|---|---|
| Lowest listed on-demand price | $0.80 per GPU-hour · AWS · checked Oct 25, 2026 | $1.35 per GPU-hour · Hyperstack · checked Oct 25, 2026 | A100 1.68× higher |
| Lowest listed spot price | No fresh listing | $1.06 per GPU-hour · Microsoft Azure · checked Oct 25, 2026 | — |
| Price per GB of memory | $0.034 per GB of GPU memory per hour | $0.017 per GB of GPU memory per hour | L4 1.99× higher |
| Fresh listings | 4 from 2 providers | 14 from 9 providers | — |
Prices cover every version and instance size the providers list, so they are not tied to the versions compared above; the price per GB of memory divides the lowest fresh on-demand price by the memory of the compared version. Listed prices are not like for like across providers. See every listing: L4 prices · A100 prices.
More on these GPUs
Cite this page
Last updated Oct 25, 2026. Figures may change as records are updated — include the date you retrieved them.
| APA | Data Center Census. (2026). L4 vs A100. Retrieved from https://datacentercensus.com/gpu-prices/compare/l4-vs-a100 |
|---|---|
| MLA | “L4 vs A100.” Data Center Census, Oct 25, 2026, https://datacentercensus.com/gpu-prices/compare/l4-vs-a100. |
| Link | https://datacentercensus.com/gpu-prices/compare/l4-vs-a100 |
Republishing a figure or table? Attribute it to Data Center Census with a link to this page. The underlying data is downloadable as JSON and CSV; the press kit has standing figures and contact details.