Specifications Compared
| Spec | L40 | RTX 5090 |
|---|---|---|
| TDP | 300W | 575W |
| VRAM | 48 GB | 32 GB |
| CUDA Cores | 18,176 | 21,760 |
| FP4 (dense) | Not published | 1,676 TFLOPS |
| FP8 (dense) | 362 TFLOPS | 419 TFLOPS |
| Memory Type | GDDR6 | GDDR7 |
| Architecture | Ada Lovelace | Blackwell |
| FP16 (dense) | 181.05 TFLOPS | 209.5 TFLOPS |
| Form Factors | PCIe | PCIe |
| INT8 (dense) | 362 TOPS | 838 TOPS |
| Interconnect | PCIe 4.0 | PCIe 5.0 |
| Tensor Cores | 568 | 680 |
| FP32 Performance | 90.5 TFLOPS | 104.8 TFLOPS |
| FP64 Performance | Not published | 1.6 TFLOPS |
| Memory Bandwidth | 864 GB/s | 1,792 GB/s |
| FP4 (with sparsity) | Not published | 3,352 TFLOPS |
| FP8 (with sparsity) | 724 TFLOPS | 838 TFLOPS |
| FP16 (with sparsity) | 362.1 TFLOPS | 419 TFLOPS |
| INT8 (with sparsity) | 724 TOPS | 1,676 TOPS |
Performance Analysis
The RTX 5090 provides 209.5 TFLOPS dense FP16 compared to 181.05 TFLOPS dense FP16 on the L40, which produces a 1.16 times advantage in dense FP16 throughput. Both GPUs maintain an exact 2 times ratio of dense FP16 to FP32, so the L40 yields 181.05 TFLOPS dense FP16 against 90.5 TFLOPS FP32 while the RTX 5090 yields 209.5 TFLOPS dense FP16 against 104.8 TFLOPS FP32. Memory bandwidth on the RTX 5090 reaches 1792 GB/s versus 864 GB/s on the L40, which supports larger batch sizes during training and inference. Sparse FP16 figures follow the same pattern with the RTX 5090 at 419 TFLOPS against 362.1 TFLOPS on the L40.
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.
L40
| Provider | Region | GPUs | Per GPU / hr | Instance / hr | Deploy |
|---|---|---|---|---|---|
| ThunderCompute | USA | 2 | $0.79 | $1.58 | Deploy |
| RunPod | global | 1 | $0.82 | — | Deploy |
| Massed Compute | us-central-3 | 1 | $0.86 | — | Deploy |
| QuantaCloud | us-midwest-2 | 4 | $0.94 | $3.75 | Deploy |
| Hyperstack | CANADA-1 | 1 | $1.00 | — | Deploy |
5 providers in stock, 14 offers (cheapest per provider shown). All L40 offers, price history and alerts
Notify me when L40 drops below a price
One email when the cheapest in-stock on-demand price per GPU-hour falls below your threshold. Cheapest right now: $0.79/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 L40
The L40 suits deployments that require 48 GB VRAM for models exceeding 32 GB capacity. Its 300W TDP also fits environments with strict power limits where the RTX 5090 575W rating exceeds available headroom.
When to Choose the RTX 5090
Its PCIe 5.0 interconnect further accelerates data movement compared to the L40 PCIe 4.0 link.
Use Cases
The L40 supplies 48 GB VRAM which accommodates larger models than the 32 GB on the RTX 5090.
The RTX 5090 achieves 209.5 TFLOPS dense FP16 and 1792 GB/s bandwidth for reduced latency over the L40 figures.
The L40 48 GB VRAM supports fine-tuning of models that exceed the 32 GB limit of the RTX 5090.
The RTX 5090 209.5 TFLOPS dense FP16 and double the bandwidth enable higher throughput than the L40.
The L40 300W TDP operates within lower power envelopes than the 575W rating of the RTX 5090.
Frequently Asked Questions
What is the memory bandwidth comparison?▾
The RTX 5090 reaches 1792 GB/s while the L40 reaches 864 GB/s. The higher figure on the RTX 5090 supports larger batch sizes in memory-bound tasks.
Which GPU has higher dense FP16 performance?▾
The RTX 5090 lists 209.5 TFLOPS dense FP16 compared to 181.05 TFLOPS dense FP16 on the L40. Both values represent dense operation without sparsity.
How do the TDP values compare?▾
The L40 TDP is 300W and the RTX 5090 TDP is 575W. Power delivery systems must accommodate the higher rating on the RTX 5090.
What interconnect does each GPU use?▾
The L40 uses PCIe 4.0 and the RTX 5090 uses PCIe 5.0. The newer standard on the RTX 5090 increases theoretical transfer rates.
Do both GPUs support sparse FP16?▾
Yes. The L40 reaches 362.1 TFLOPS with sparsity and the RTX 5090 reaches 419 TFLOPS with sparsity. These figures must be compared only to other sparse values.
Which is cheaper to rent, the L40 or the RTX 5090?▾
Cloud rental prices for both the L40 and RTX 5090 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 L40 have compared to the RTX 5090?▾
The L40 has 48 GB of GDDR6 memory. The RTX 5090 has 32 GB of GDDR7 memory.
Can I find L40 and RTX 5090 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 L40 and the RTX 5090?▾
The L40 uses the Ada Lovelace architecture (2023) while the RTX 5090 uses Blackwell (2025). The RTX 5090 delivers 1.2x the dense FP16 throughput (209.5 vs 181.05 TFLOPS, both without sparsity) and 2.1x the memory bandwidth of the L40.
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 L40 and the RTX 5090. 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 L40Every current offer by provider, daily price history and a price alert.
- Rent RTX 5090Every 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.