Specifications Compared
| Spec | L40S | T4 |
|---|---|---|
| TDP | 350W | 70W |
| VRAM | 48 GB | 16 GB |
| CUDA Cores | 18,176 | 2,560 |
| FP8 (dense) | 733 TFLOPS | Not published |
| Memory Type | GDDR6 | GDDR6 |
| Architecture | Ada Lovelace | Turing |
| FP16 (dense) | 362.05 TFLOPS | 65 TFLOPS |
| Form Factors | PCIe | PCIe |
| INT8 (dense) | 733 TOPS | 130 TOPS |
| Interconnect | PCIe 4.0 | PCIe 3.0 |
| Tensor Cores | 568 | 320 |
| FP32 Performance | 91.6 TFLOPS | 8.1 TFLOPS |
| FP64 Performance | 1.4 TFLOPS | Not published |
| Memory Bandwidth | 864 GB/s | 320 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 |
Performance Analysis
FP16 dense performance measures 362.05 TFLOPS on the L40S against 65 TFLOPS on the T4. FP32 performance reaches 91.6 TFLOPS on the L40S versus 8.1 TFLOPS on the T4. The ratio of FP16 dense to FP32 therefore equals roughly four times on the L40S and eight times on the T4. FP16 with sparsity attains 733 TFLOPS on the L40S while the T4 figure remains unavailable for comparison. Memory bandwidth of 864 GB/s on the L40S versus 320 GB/s on the T4 permits larger batch sizes during both training and inference workloads. INT8 dense performance equals 733 TOPS on the L40S against 130 TOPS on the T4.
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-1 | 4 | $1.09 | $4.36 | Deploy |
| RunPod | global | 1 | $1.09 | — | Deploy |
| Lyceum | Europe | 2 | $1.99 | $3.98 | Deploy |
4 providers in stock, 18 offers (cheapest per provider shown). All L40S offers, price history and alerts
T4
T4 is not offered on-demand by any provider we track right now. See the T4 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 suits workloads that require 48 GB GDDR6 VRAM and 864 GB/s memory bandwidth. FP16 dense throughput of 362.05 TFLOPS supports accelerated training and inference relative to older hardware. PCIe 4.0 interconnect further aids multi GPU scaling in dense compute environments.
When to Choose the T4
The T4 fits deployments constrained to 70 W TDP and 16 GB GDDR6 VRAM. FP32 performance of 8.1 TFLOPS remains adequate for lighter inference tasks where power efficiency takes priority over peak throughput.
Use Cases
The L40S supplies 48 GB GDDR6 VRAM and 362.05 TFLOPS FP16 dense performance while the T4 offers only 16 GB GDDR6 VRAM and 65 TFLOPS FP16 dense performance.
The L40S provides 733 TFLOPS FP16 with sparsity and 864 GB/s memory bandwidth enabling larger batch sizes than the T4 320 GB/s memory bandwidth.
The L40S 48 GB GDDR6 VRAM and 733 TOPS INT8 dense rating accommodate fine tuning workloads beyond the T4 16 GB GDDR6 VRAM and 130 TOPS INT8 dense rating.
The L40S FP16 dense rating of 362.05 TFLOPS and 48 GB GDDR6 VRAM exceed the T4 FP16 dense rating of 65 TFLOPS and 16 GB GDDR6 VRAM.
The L40S offers higher FP32 performance at 91.6 TFLOPS while the T4 operates at 70 W TDP which may suit power limited scientific nodes.
Frequently Asked Questions
What is the FP16 dense performance difference between L40S and T4?▾
The L40S reaches 362.05 TFLOPS FP16 dense. The T4 reaches 65 TFLOPS FP16 dense.
Which GPU has higher memory bandwidth L40S or T4?▾
The L40S achieves 864 GB/s memory bandwidth. The T4 achieves 320 GB/s memory bandwidth.
What TDP values separate the L40S from the T4?▾
The L40S lists 350 W TDP. The T4 lists 70 W TDP.
Does the L40S support higher INT8 dense performance than the T4?▾
The L40S delivers 733 TOPS INT8 dense. The T4 delivers 130 TOPS INT8 dense.
What FP32 performance do the L40S and T4 provide?▾
The L40S supplies 91.6 TFLOPS FP32. The T4 supplies 8.1 TFLOPS FP32.
Which is cheaper to rent, the L40S or the T4?▾
Cloud rental prices for both the L40S and T4 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 T4?▾
The L40S has 48 GB of GDDR6 memory. The T4 has 16 GB of GDDR6 memory.
Can I find L40S and T4 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 T4?▾
The L40S uses the Ada Lovelace architecture (2023) while the T4 uses Turing (2018). The L40S delivers 5.6x the dense FP16 throughput (362.05 vs 65 TFLOPS, both without sparsity) and 2.7x the memory bandwidth of the T4.
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 T4. 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 T4Every 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.