Specifications Compared
| Spec | L40S | RTX 4080 SUPER |
|---|---|---|
| TDP | 350W | 320W |
| VRAM | 48 GB | 16 GB |
| CUDA Cores | 18,176 | 9,728 |
| FP8 (dense) | 733 TFLOPS | Not published |
| Memory Type | GDDR6 | GDDR6X |
| Architecture | Ada Lovelace | Ada Lovelace |
| FP16 (dense) | 362.05 TFLOPS | Not published |
| Form Factors | PCIe | PCIe |
| INT8 (dense) | 733 TOPS | Not published |
| Interconnect | PCIe 4.0 | Not published |
| Tensor Cores | 568 | 304 |
| FP32 Performance | 91.6 TFLOPS | 48.7 TFLOPS |
| FP64 Performance | 1.4 TFLOPS | Not published |
| Memory Bandwidth | 864 GB/s | 717 GB/s |
| FP8 (with sparsity) | 1,466 TFLOPS | Not published |
| FP16 (with sparsity) | 733 TFLOPS | Not published |
| INT8 (with sparsity) | 1,466 TOPS | Not published |
| FP16 (vendor figure, sparsity not specified) | Not published | 48.7 TFLOPS |
| INT8 (vendor figure, sparsity not specified) | Not published | 780 TOPS |
Performance Analysis
The L40S family delivers FP16 dense performance at 362.05 TFLOPS compared to the RTX 4080 family FP16 figure of 48.7 TFLOPS where sparsity remains unspecified. This dense FP16 gap means the L40S processes matrix operations over seven times faster during training and inference workloads. Memory bandwidth of 864 GB/s shared by all L40S variants versus 717 GB/s shared by all RTX 4080 variants allows larger batch sizes on the L40S before memory constraints appear. FP32 performance reaches 91.6 TFLOPS on the L40S family against 48.7 TFLOPS on the RTX 4080 family.
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
RTX 4080 SUPER
RTX 4080 SUPER is not offered on-demand by any provider we track right now. See the RTX 4080 SUPER rental page for last-seen listed prices and a price alert.
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 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 L40S
The L40S variant suits large model training that requires the full 48 GB memory capacity and 362.05 TFLOPS dense FP16 throughput. Its 864 GB/s bandwidth supports sustained high throughput on memory intensive scientific computing tasks.
When to Choose the RTX 4080 SUPER
The RTX 4080 SUPER variant fits lighter inference workloads that fit within 16 GB and benefit from its 320 W TDP shared across the family. Its 48.7 TFLOPS FP16 rating handles smaller batch stable diffusion jobs without excess power draw.
Use Cases
The L40S variant supplies 48 GB memory and 362.05 TFLOPS dense FP16 that accommodate large models without frequent swapping.
The L40S variant processes requests at 362.05 TFLOPS dense FP16 while the 48 GB capacity holds extended context windows.
The L40S variant offers 733 TFLOPS FP8 dense throughput and 48 GB memory for efficient parameter updates on sizable datasets.
The RTX 4080 SUPER variant manages typical image generation tasks inside its 16 GB memory at 48.7 TFLOPS FP16.
The L40S variant provides 91.6 TFLOPS FP32 and 864 GB/s bandwidth for compute heavy simulations.
Frequently Asked Questions
What memory difference exists between these variants?▾
The L40S variant contains 48 GB GDDR6 while the RTX 4080 SUPER variant holds 16 GB GDDR6X. This capacity gap directly limits model size on the latter.
How do the FP16 figures compare?▾
The L40S family reports 362.05 TFLOPS dense FP16 against the RTX 4080 family value of 48.7 TFLOPS. Sparsity applies only to the L40S numbers.
Which TDP applies to each variant?▾
The L40S family shares a 350 W TDP while the RTX 4080 family shares a 320 W TDP. These values remain constant across variants within each family.
What bandwidth do the families provide?▾
All L40S variants share 864 GB/s bandwidth and all RTX 4080 variants share 717 GB/s bandwidth. The difference affects data movement rates during training.
Do both variants use the same architecture?▾
Both variants employ the Ada Lovelace architecture though the L40S dates to 2023 and the RTX 4080 SUPER to 2022. Form factors remain PCIe for each.
Which variant handles larger INT8 workloads?▾
The L40S family supplies 733 TOPS dense INT8 while the RTX 4080 family lists 780 TOPS without sparsity detail. Memory capacity still favors the L40S for big models.
Which is cheaper to rent, the L40S or the RTX 4080 SUPER?▾
Cloud rental prices for both the L40S and RTX 4080 SUPER 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 RTX 4080 SUPER?▾
The L40S has 48 GB of GDDR6 memory. The RTX 4080 SUPER has 16 GB of GDDR6X memory.
Can I find L40S and RTX 4080 SUPER 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 RTX 4080 SUPER?▾
The L40S uses the Ada Lovelace architecture (2023) while the RTX 4080 SUPER uses Ada Lovelace (2022). The L40S delivers 3.7x the dense FP16 throughput (362.05 vs 97.5 TFLOPS, both without sparsity) and 1.2x the memory bandwidth of the RTX 4080 SUPER.
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 RTX 4080 SUPER. 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 RTX 4080Every 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.