Specifications Compared
| Spec | A100 PCIe 80GB | L40S |
|---|---|---|
| TDP | 400W | 350W |
| VRAM | 80 GB | 48 GB |
| CUDA Cores | 6,912 | 18,176 |
| FP8 (dense) | Not published | 733 TFLOPS |
| Memory Type | HBM2e | GDDR6 |
| Architecture | Ampere | Ada Lovelace |
| FP16 (dense) | 312 TFLOPS | 362.05 TFLOPS |
| Form Factors | PCIe | PCIe |
| INT8 (dense) | 624 TOPS | 733 TOPS |
| Interconnect | PCIe 4.0, InfiniBand; NVLink only via a bridge between card pairs | PCIe 4.0 |
| Tensor Cores | 432 | 568 |
| FP32 Performance | 19.5 TFLOPS | 91.6 TFLOPS |
| FP64 Performance | 9.7 TFLOPS | 1.4 TFLOPS |
| Memory Bandwidth | 2,039 GB/s | 864 GB/s |
| FP8 (with sparsity) | Not published | 1,466 TFLOPS |
| FP16 (with sparsity) | 624 TFLOPS | 733 TFLOPS |
| INT8 (with sparsity) | 1,248 TOPS | 1,466 TOPS |
Performance Analysis
Dense FP16 throughput measures 312 TFLOPS on the A100 family against 362.05 TFLOPS on the L40S family while sparse FP16 reaches 624 TFLOPS versus 733 TFLOPS respectively. The higher dense FP16 and FP32 figures of 91.6 TFLOPS on the L40S family compared with 19.5 TFLOPS on the A100 family translate to faster matrix operations during inference workloads that fit within 48 GB. Memory bandwidth of 2039 GB/s on the A100 family supports larger batch sizes in memory intensive training scenarios than the 864 GB/s bandwidth on the L40S family even though both families share their tensor metrics across variants.
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.
A100 PCIe 80GB
| 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 | 1 | $1.09 | — | Deploy |
| Hyperstack | CANADA-1 | 1 | $1.35 | — | Deploy |
| Massed Compute | us-east-1 | 1 | $1.38 | — | Deploy |
10 providers in stock, 30 offers (cheapest per provider shown). All A100 PCIe 80GB offers, price history and alerts
L40S
| Provider | Region | GPUs | Per GPU / hr | Instance / hr | Deploy |
|---|---|---|---|---|---|
| Massed Compute | us-central-3 | 4 | $0.97 | $3.88 | Deploy |
| QuantaCloud | us-midwest-1 | 4 | $1.09 | $4.36 | Deploy |
| RunPod | global | 1 | $1.09 | — | Deploy |
| Lyceum | Europe | 1 | $1.99 | — | Deploy |
4 providers in stock, 18 offers (cheapest per provider shown). All L40S offers, price history and alerts
Notify me when A100 PCIe 80GB drops below a price
One email when the cheapest in-stock on-demand price per GPU-hour falls below your threshold. Cheapest right now: $0.68/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 A100 PCIe 80GB
The A100 PCIe 80GB variant suits workloads that require 80 GB HBM2e capacity for models exceeding 48 GB. Its 2039 GB/s memory bandwidth and InfiniBand interconnect enable distributed training across multiple cards where the L40S variant cannot match the memory scale.
When to Choose the L40S
Its 350W TDP and Ada Lovelace architecture deliver higher per watt tensor performance than the A100 PCIe 80GB variant for single node deployments.
Use Cases
The A100 PCIe 80GB variant provides 80 GB HBM2e that accommodates larger models than the 48 GB GDDR6 on the L40S variant.
The L40S variant supplies 362.05 TFLOPS dense FP16 that exceeds the 312 TFLOPS dense FP16 of the A100 family for smaller batches.
The L40S variant offers 91.6 TFLOPS FP32 and lower 350W TDP that improve efficiency over the A100 PCIe 80GB variant for adapter based updates.
The A100 PCIe 80GB variant supports 80 GB capacity that allows higher resolution batches than the 48 GB limit of the L40S variant.
The A100 PCIe 80GB variant includes InfiniBand interconnect and 2039 GB/s bandwidth that aid multi node scientific simulations.
Frequently Asked Questions
What is the memory difference between A100 PCIe 80GB and L40S?▾
The A100 PCIe 80GB variant holds 80 GB HBM2e while the L40S variant holds 48 GB GDDR6. Both families share their listed memory bandwidth figures across all variants.
How does FP16 performance compare between these GPUs?▾
Dense FP16 reaches 312 TFLOPS on the A100 family and 362.05 TFLOPS on the L40S family. Sparse FP16 reaches 624 TFLOPS on the A100 family and 733 TFLOPS on the L40S family.
Which GPU has higher FP32 throughput?▾
The L40S family lists 91.6 TFLOPS FP32 while the A100 family lists 19.5 TFLOPS FP32. These figures apply to every variant within each family.
Can the A100 PCIe 80GB use NVLink?▾
The A100 PCIe 80GB variant supports NVLink only through a bridge between card pairs along with InfiniBand. The L40S variant supports only PCIe 4.0 interconnect.
What are the TDP values for each GPU?▾
The A100 family TDP is 400W and the L40S family TDP is 350W. These power figures remain consistent across all variants of each family.
Which is cheaper to rent, the A100 PCIe 80GB or the L40S?▾
Cloud rental prices for both the A100 PCIe 80GB and L40S 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 A100 PCIe 80GB have compared to the L40S?▾
The A100 PCIe 80GB has 80 GB of HBM2e memory. The L40S has 48 GB of GDDR6 memory.
Can I find A100 PCIe 80GB and L40S 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 A100 PCIe 80GB and the L40S?▾
The A100 PCIe 80GB uses the Ampere architecture (2020) while the L40S uses Ada Lovelace (2023). The L40S delivers 1.2x the dense FP16 throughput (362.05 vs 312 TFLOPS, both without sparsity) while the A100 PCIe 80GB 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 A100 PCIe 80GB and the L40S. 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 A100Every current offer by provider, daily price history and a price alert.
- Rent L40SEvery 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.