Specifications Compared
| Spec | L40 | RTX 3080 |
|---|---|---|
| TDP | 300W | 320W |
| VRAM | 48 GB | 10-12 GB |
| CUDA Cores | 18,176 | 8,704 |
| FP8 (dense) | 362 TFLOPS | Not published |
| Memory Type | GDDR6 | GDDR6X |
| Architecture | Ada Lovelace | Ampere |
| FP16 (dense) | 181.05 TFLOPS | 59.5 TFLOPS |
| Form Factors | PCIe | PCIe |
| INT8 (dense) | 362 TOPS | 238 TOPS |
| Interconnect | PCIe 4.0 | PCIe 4.0 |
| Tensor Cores | 568 | 272 |
| FP32 Performance | 90.5 TFLOPS | 29.8 TFLOPS |
| Memory Bandwidth | 864 GB/s | 760 GB/s |
| FP8 (with sparsity) | 724 TFLOPS | Not published |
| FP16 (with sparsity) | 362.1 TFLOPS | 119 TFLOPS |
| INT8 (with sparsity) | 724 TOPS | 476 TOPS |
Performance Analysis
The FP16 dense figure of 181.05 TFLOPS on the L40 exceeds the FP16 dense figure of 59.5 TFLOPS on the RTX 3080 by a ratio of three to one. The FP16 with sparsity figure of 362.1 TFLOPS on the L40 exceeds the FP16 with sparsity figure of 119 TFLOPS on the RTX 3080 by a similar ratio. Such deltas indicate that the L40 supports larger batch sizes during training or inference steps that rely on FP16 dense or FP16 with sparsity operations. Memory bandwidth of 864 GB/s on the L40 versus 760 GB/s on the RTX 3080 further influences achievable batch sizes in bandwidth bound scenarios. The FP32 value of 90.5 TFLOPS on the L40 compared to 29.8 TFLOPS on the RTX 3080 shows a three to one advantage for dense single precision workloads.
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 | 1 | $0.79 | — | Deploy |
| Massed Compute | us-central-2 | 1 | $0.86 | — | Deploy |
| QuantaCloud | us-midwest-2 | 4 | $0.94 | $3.75 | Deploy |
| Hyperstack | CANADA-1 | 4 | $1.00 | $4.00 | Deploy |
4 providers in stock, 17 offers (cheapest per provider shown). All L40 offers, price history and alerts
RTX 3080
RTX 3080 is not offered on-demand by any provider we track right now. See the RTX 3080 rental page for last-seen listed prices and a price alert.
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 workloads that require 48 GB of GDDR6 memory for large model states. Its FP16 dense performance of 181.05 TFLOPS and FP8 dense performance of 362 TFLOPS support higher throughput in tensor operations compared to the RTX 3080. The 300W TDP also reduces power draw relative to the 320W TDP of the RTX 3080 in sustained runs.
When to Choose the RTX 3080
The RTX 3080 fits scenarios where 10 to 12 GB of GDDR6X memory suffices and lower acquisition considerations apply. Its INT8 dense performance of 238 TOPS remains adequate for lighter inference tasks that do not demand the 362 TOPS INT8 dense rating of the L40.
Use Cases
The L40 provides 48 GB GDDR6 memory and FP16 dense performance of 181.05 TFLOPS for larger training batches.
The L40 delivers FP16 dense performance of 181.05 TFLOPS and 48 GB memory to handle bigger models at higher throughput.
The L40 offers 48 GB GDDR6 memory and FP16 with sparsity performance of 362.1 TFLOPS for efficient parameter updates.
The L40 supplies 48 GB GDDR6 memory and FP16 dense performance of 181.05 TFLOPS for high resolution image generation.
The L40 provides an FP32 rating of 90.5 TFLOPS and 864 GB/s bandwidth for compute heavy simulations.
Frequently Asked Questions
How does FP16 dense performance compare?▾
The L40 achieves 181.05 TFLOPS in FP16 dense while the RTX 3080 achieves 59.5 TFLOPS in FP16 dense. The ratio favors the L40 for FP16 dense workloads by three to one.
What are the TDP values for each GPU?▾
The L40 lists a TDP of 300W and the RTX 3080 lists a TDP of 320W. Lower power draw on the L40 can reduce operating costs in continuous operation.
Which GPU has higher memory bandwidth?▾
The L40 provides 864 GB/s of memory bandwidth while the RTX 3080 provides 760 GB/s. The higher bandwidth on the L40 supports larger batch sizes in bandwidth limited tasks.
Can the RTX 3080 match L40 FP32 performance?▾
The RTX 3080 reaches 29.8 TFLOPS in FP32 while the L40 reaches 90.5 TFLOPS in FP32. The L40 maintains a three to one advantage in FP32 dense operations.
Which is cheaper to rent, the L40 or the RTX 3080?▾
Cloud rental prices for both the L40 and RTX 3080 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 3080?▾
The L40 has 48 GB of GDDR6 memory. The RTX 3080 has 10 to 12 GB of GDDR6X memory.
Can I find L40 and RTX 3080 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 3080?▾
The L40 uses the Ada Lovelace architecture (2023) while the RTX 3080 uses Ampere (2020). The L40 delivers 3.0x the dense FP16 throughput (181.05 vs 59.5 TFLOPS, both without sparsity) and 1.1x the memory bandwidth of the RTX 3080.
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 3080. 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 3080Every 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.