Specifications Compared
| Spec | A40 | L4 |
|---|---|---|
| TDP | 300W | 72W |
| VRAM | 48 GB | 24 GB |
| CUDA Cores | 10,752 | 7,424 |
| FP8 (dense) | Not published | 242 TFLOPS |
| Memory Type | GDDR6 | GDDR6 |
| Architecture | Ampere | Ada Lovelace |
| FP16 (dense) | 149.7 TFLOPS | 121 TFLOPS |
| Form Factors | PCIe | PCIe |
| INT8 (dense) | 299.3 TOPS | 242 TOPS |
| Interconnect | NVLink, PCIe 4.0 | PCIe 4.0 |
| Tensor Cores | 336 | 232 |
| FP32 Performance | 37.4 TFLOPS | 30.3 TFLOPS |
| FP64 Performance | Not published | 0.5 TFLOPS |
| Memory Bandwidth | 696 GB/s | 300 GB/s |
| FP8 (with sparsity) | Not published | 485 TFLOPS |
| FP16 (with sparsity) | 299.4 TFLOPS | 242 TFLOPS |
| INT8 (with sparsity) | 598.6 TOPS | 485 TOPS |
Performance Analysis
Dense FP16 performance stands at 149.7 TFLOPS on the A40 versus 121 TFLOPS on the L4. Sparse FP16 reaches 299.4 TFLOPS on the A40 and 242 TFLOPS on the L4. The FP16 to FP32 ratio equals 4.0 on the A40 and 4.0 on the L4 indicating similar acceleration for mixed precision training. Memory bandwidth of 696 GB/s on the A40 versus 300 GB/s on the L4 permits larger batch sizes during inference and training. Dense INT8 performance measures 299.3 TOPS on the A40 against 242 TOPS on the L4 while sparse INT8 reaches 598.6 TOPS versus 485 TOPS.
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.
A40
| Provider | Region | GPUs | Per GPU / hr | Instance / hr | Deploy |
|---|---|---|---|---|---|
| LeaderGPU | The Netherlands | 8 | $0.52 | $4.13 | Deploy |
| RunPod | global | 1 | $0.59 | — | Deploy |
2 providers in stock, 2 offers. All A40 offers, price history and alerts
L4
2 providers in stock, 2 offers. All L4 offers, price history and alerts
Notify me when A40 drops below a price
One email when the cheapest in-stock on-demand price per GPU-hour falls below your threshold. Cheapest right now: $0.52/GPU-hr.
QuantaCloud
Comparing providers? We broker across all of them.
Stop tab-switching between pricing pages. Tell us what you need, 16+ GPUs reserved or cluster capacity, and we return one quote at partner rates within 24 hours.
When to Choose the A40
The A40 suits workloads that require 48 GB VRAM and 696 GB/s bandwidth such as large model training. FP32 throughput of 37.4 TFLOPS supports scientific computing tasks that exceed the 30.3 TFLOPS of the L4. Higher dense FP16 at 149.7 TFLOPS enables faster iteration on memory heavy inference compared with the L4.
When to Choose the L4
The L4 fits deployments limited to 72 W power where the A40 300 W draw exceeds available capacity. Dense FP8 at 242 TFLOPS provides efficient inference on the L4 for lighter models that fit within 24 GB VRAM. PCIe only interconnect matches environments without NVLink infrastructure.
Use Cases
The A40 supplies 48 GB VRAM and 149.7 TFLOPS dense FP16 which exceed L4 capacity for large models.
Higher memory bandwidth of 696 GB/s on the A40 supports larger batch sizes than the 300 GB/s on the L4.
The A40 37.4 TFLOPS FP32 and 48 GB VRAM accommodate fine tuning workloads beyond L4 limits.
Both GPUs handle the task with the A40 offering more headroom and the L4 providing lower power draw.
FP32 performance of 37.4 TFLOPS on the A40 surpasses the 30.3 TFLOPS on the L4 for compute heavy jobs.
Frequently Asked Questions
How does memory bandwidth compare on A40 versus L4?▾
The A40 reaches 696 GB/s and the L4 reaches 300 GB/s. Bandwidth determines data movement speed during training and inference.
Which GPU has higher dense FP16 performance?▾
The A40 achieves 149.7 TFLOPS dense FP16 while the L4 achieves 121 TFLOPS dense FP16. The A40 therefore processes dense operations faster.
What TDP values apply to the A40 and L4?▾
The A40 TDP equals 300 W and the L4 TDP equals 72 W. Lower power on the L4 suits dense rack deployments.
Does the A40 support NVLink?▾
The A40 includes NVLink interconnect while the L4 does not. Multi GPU scaling differs accordingly between the two.
How do sparse FP16 figures compare?▾
Sparse FP16 reaches 299.4 TFLOPS on the A40 and 242 TFLOPS on the L4. The A40 maintains the advantage in sparse workloads.
Which is cheaper to rent, the A40 or the L4?▾
Cloud rental prices for both the A40 and L4 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 A40 have compared to the L4?▾
The A40 has 48 GB of GDDR6 memory. The L4 has 24 GB of GDDR6 memory.
Can I find A40 and L4 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 A40 and the L4?▾
The A40 uses the Ampere architecture (2020) while the L4 uses Ada Lovelace (2023). The A40 delivers 1.2x the dense FP16 throughput (149.7 vs 121 TFLOPS, both without sparsity) and 2.3x the memory bandwidth of the L4.
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 A40 and the L4. 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 A40Every current offer by provider, daily price history and a price alert.
- Rent L4Every 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.