Specifications Compared
| Spec | L40S | A100 |
|---|---|---|
| TDP | 350W | 400W |
| VRAM | 48 GB | 40-80 GB |
| CUDA Cores | 18,176 | 6,912 |
| FP8 (dense) | 733 TFLOPS | Not published |
| Memory Type | GDDR6 | HBM2e |
| Architecture | Ada Lovelace | Ampere |
| FP16 (dense) | 362.05 TFLOPS | 312 TFLOPS |
| Form Factors | PCIe | SXM4, PCIe |
| INT8 (dense) | 733 TOPS | 624 TOPS |
| Interconnect | PCIe 4.0 | NVLink, PCIe 4.0, InfiniBand |
| Tensor Cores | 568 | 432 |
| FP32 Performance | 91.6 TFLOPS | 19.5 TFLOPS |
| FP64 Performance | 1.4 TFLOPS | 9.7 TFLOPS |
| Memory Bandwidth | 864 GB/s | 2,039 GB/s |
| FP8 (with sparsity) | 1,466 TFLOPS | Not published |
| FP16 (with sparsity) | 733 TFLOPS | 624 TFLOPS |
| INT8 (with sparsity) | 1,466 TOPS | 1,248 TOPS |
Performance Analysis
The L40S delivers 362.05 TFLOPS dense FP16 compared to 312 TFLOPS dense FP16 on the A100 which translates to faster matrix operations in training and inference pipelines that rely on dense precision. The A100 provides 2039 GB/s memory bandwidth versus 864 GB/s on the L40S allowing larger batch sizes in memory intensive tasks. FP32 throughput stands at 91.6 TFLOPS for the L40S against 19.5 TFLOPS for the A100 indicating stronger general compute capability on the newer card. Sparsity figures follow the same pattern with the L40S at 733 TFLOPS FP16 with sparsity versus 624 TFLOPS FP16 with sparsity on the A100.
Current On-Demand Offers
Cheapest secure on-demand offer per provider that is reported in stock right now, per GPU per hour; multi-GPU instances show the whole-instance price alongside. Deploy opens the DeployGPU console for providers on the platform, otherwise the provider's own site. Stock is rechecked every minute.
L40S
| Provider | Region | GPUs | Per GPU / hr | Instance / hr | Deploy |
|---|---|---|---|---|---|
| Massed Compute | us-central-3 | 4 | $0.97 | $3.88 | Deploy |
| QuantaCloud | us-midwest-2 | 1 | $1.09 | — | Deploy |
| RunPod | global | 1 | $1.09 | — | Deploy |
| Ori | lille-4 | 1 | $1.55 | — | Deploy |
| VERDA | FIN-HEL | 1 | $1.77 | — | Deploy |
6 providers in stock, 19 offers (cheapest per provider shown). All L40S offers, price history and alerts
A100
| Provider | Region | GPUs | Per GPU / hr | Instance / hr | Deploy |
|---|---|---|---|---|---|
| LeaderGPU | The Netherlands | 8 | $0.68 | $5.42 | Deploy |
| Vast.ai | Czechia, CZ | 1 | $0.73 | — | Deploy |
| ThunderCompute | USA | 2 | $1.09 | $2.18 | Deploy |
| Massed Compute | us-east-1 | 1 | $1.38 | — | Deploy |
| QuantaCloud | us-east-1 | 8 | $1.50 | $11.97 | Deploy |
12 providers in stock, 36 offers (cheapest per provider shown). All A100 offers, price history and alerts
Notify me when L40S drops below a price
One email when the cheapest in-stock on-demand price per GPU-hour falls below your threshold. Cheapest right now: $0.97/GPU-hr.
QuantaCloud
Comparing A100 providers? We broker across all of them.
Need 16+ A100s reserved for fine-tuning, simulation, or production inference? We quote volume pricing across multiple data center partners: one quote at partner rates, 24h turnaround.
When to Choose the L40S
The L40S suits environments that prioritize 91.6 TFLOPS FP32 performance and 350W TDP limits. Its 362.05 TFLOPS dense FP16 and 733 TFLOPS FP8 dense make it preferable for inference workloads that fit within 48 GB GDDR6 capacity and PCIe interconnect constraints.
When to Choose the A100
The A100 fits scenarios that demand 2039 GB/s memory bandwidth and NVLink interconnect options. Its support for up to 80 GB HBM2e VRAM enables larger models in training or inference compared to the fixed 48 GB on the L40S.
Use Cases
The A100 supplies 2039 GB/s memory bandwidth and up to 80 GB VRAM which support larger training batches than the L40S 864 GB/s and 48 GB configuration.
The L40S provides 362.05 TFLOPS dense FP16 and 733 TFLOPS FP8 dense which exceed the A100 dense FP16 figure of 312 TFLOPS.
The L40S achieves 91.6 TFLOPS FP32 and 362.05 TFLOPS dense FP16 at 350W TDP making it efficient for adaptation workloads.
The L40S FP8 dense performance reaches 733 TFLOPS which surpasses A100 tensor capabilities in this precision.
The L40S delivers 91.6 TFLOPS FP32 compared to 19.5 TFLOPS FP32 on the A100 for general numeric workloads.
Frequently Asked Questions
What is the FP16 dense performance difference between L40S and A100?▾
The L40S reaches 362.05 TFLOPS dense FP16 while the A100 reaches 312 TFLOPS dense FP16. This gap favors the L40S in dense tensor operations.
How does memory bandwidth compare on L40S versus A100?▾
The L40S provides 864 GB/s memory bandwidth whereas the A100 provides 2039 GB/s. Higher bandwidth on the A100 supports larger data movements.
Which GPU has lower power consumption L40S or A100?▾
The L40S operates at 350W TDP while the A100 operates at 400W TDP. The L40S therefore consumes less power under load.
What interconnect options exist on each GPU?▾
The L40S uses PCIe 4.0 only. The A100 supports NVLink in addition to PCIe 4.0 and InfiniBand.
Which is cheaper to rent, the L40S or the A100?▾
Cloud rental prices for both the L40S and A100 vary by provider, configuration, and availability. This page shows live pricing from 25+ providers updated every 60 seconds. Scroll to the Live Cloud Pricing section to compare current rates.
How much VRAM does the L40S have compared to the A100?▾
The L40S has 48 GB of GDDR6 memory. The A100 has 40 to 80 GB of HBM2e memory.
Can I find L40S and A100 GPUs available to rent right now?▾
Yes. This page shows real-time availability across 25+ cloud GPU providers. The Live Cloud Pricing section displays only in-stock offers with current pricing.
What is the main difference between the L40S and the A100?▾
The L40S uses the Ada Lovelace architecture (2023) while the A100 uses Ampere (2020). The L40S delivers 1.2x the dense FP16 throughput (362.05 vs 312 TFLOPS, both without sparsity) while the A100 has 2.4x the memory bandwidth of the L40S.
Rent these GPUs
Each GPU page lists every current on-demand offer by provider, per GPU-hour, updated every minute.
Related comparisons
How this page is made
- Specifications come from the NVIDIA, AMD and Intel datasheets for the L40S and the A100. Dense and sparse throughput are listed separately.
- Prices and availability are live: every offer shown is an in-stock, on-demand listing from a provider we track, rechecked every minute.
- The written comparison (overview, performance notes, when to choose each card, verdict, use cases and FAQ) was drafted with an AI model from the specification table above and passed an automated check that rejects any figure not in that table. It was last generated on . It contains no prices; those are always read live.
- Read how we collect the data, or report an error on this page.
Next steps
- Rent L40SEvery current offer by provider, daily price history and a price alert.
- Rent A100Every current offer by provider, daily price history and a price alert.
- GPU price indexHow on-demand prices for the major GPUs have moved, updated daily.
- All GPUsEvery GPU we track, with current lows and provider counts.