Specifications Compared
| Spec | L40 | RTX PRO 6000 |
|---|---|---|
| TDP | 300W | 600W |
| VRAM | 48 GB | 96 GB |
| CUDA Cores | 18,176 | 24,064 |
| FP4 (dense) | Not published | 2,015.2 TFLOPS |
| FP8 (dense) | 362 TFLOPS | 1,007.6 TFLOPS |
| Memory Type | GDDR6 | GDDR7 |
| Architecture | Ada Lovelace | Blackwell |
| FP16 (dense) | 181.05 TFLOPS | 503.8 TFLOPS |
| Form Factors | PCIe | PCIe |
| INT8 (dense) | 362 TOPS | 1,007.6 TOPS |
| Interconnect | PCIe 4.0 | PCIe 5.0 |
| Tensor Cores | 568 | 752 |
| FP32 Performance | 90.5 TFLOPS | 126 TFLOPS |
| Memory Bandwidth | 864 GB/s | 1,792 GB/s |
| FP4 (with sparsity) | Not published | 4,030.4 TFLOPS |
| FP8 (with sparsity) | 724 TFLOPS | 2,015.2 TFLOPS |
| FP16 (with sparsity) | 362.1 TFLOPS | 1,007.6 TFLOPS |
| INT8 (with sparsity) | 724 TOPS | 2,015.2 TOPS |
Performance Analysis
The FP16 dense performance of 503.8 TFLOPS on the RTX PRO 6000 exceeds the 181.05 TFLOPS dense performance on the L40. This difference shortens training iterations and raises inference throughput for workloads that rely on dense FP16 arithmetic. The FP16 with sparsity reaches 1007.6 TFLOPS on the RTX PRO 6000 versus 362.1 TFLOPS on the L40. Memory bandwidth of 1792 GB/s on the RTX PRO 6000 permits larger batch sizes than the 864 GB/s bandwidth on the L40. FP32 performance of 126 TFLOPS versus 90.5 TFLOPS produces corresponding gains in precision-sensitive scientific calculations when dense figures are compared directly.
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 |
| 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 | 4 | $1.00 | $4.00 | Deploy |
5 providers in stock, 16 offers (cheapest per provider shown). All L40 offers, price history and alerts
RTX PRO 6000
| Provider | Region | GPUs | Per GPU / hr | Instance / hr | Deploy |
|---|---|---|---|---|---|
| RunPod | global | 1 | $0.69 | — | Deploy |
| Vast.ai | Czechia, CZ | 1 | $1.53 | — | Deploy |
| Massed Compute | us-central-9 | 4 | $2.19 | $8.76 | Deploy |
| VERDA | FIN-HEL | 4 | $2.37 | $9.48 | Deploy |
| QuantaCloud | us-midwest-4 | 4 | $2.38 | $9.53 | Deploy |
6 providers in stock, 23 offers (cheapest per provider shown). All RTX PRO 6000 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 fits power-constrained deployments because its TDP equals 300W. Workloads that remain within 48 GB VRAM avoid the higher 600W draw of the alternative. The FP16 dense rating of 181.05 TFLOPS still sustains moderate inference tasks at lower overall system power.
When to Choose the RTX PRO 6000
The RTX PRO 6000 fits memory-intensive applications because its 96 GB capacity doubles the 48 GB available on the L40. The 1792 GB/s bandwidth and 503.8 TFLOPS dense FP16 rating accelerate large-batch inference and training. PCIe 5.0 interconnect further reduces data transfer latency compared with PCIe 4.0.
Use Cases
The 96 GB VRAM and 503.8 TFLOPS dense FP16 exceed the 48 GB and 181.05 TFLOPS on the L40.
The 1792 GB/s bandwidth and 1007.6 TFLOPS FP8 dense rating support higher throughput than the L40 figures.
The doubled memory capacity of 96 GB accommodates larger adapter sets than the 48 GB on the L40.
The 96 GB GDDR7 and 1792 GB/s bandwidth handle higher resolution generations than the L40 specifications.
The 300W TDP and 90.5 TFLOPS FP32 rating provide adequate performance at half the power of the RTX PRO 6000.
Frequently Asked Questions
How do the FP16 dense ratings compare?▾
The L40 reaches 181.05 TFLOPS dense FP16. The RTX PRO 6000 reaches 503.8 TFLOPS dense FP16. The ratio favors the RTX PRO 6000 for dense workloads.
What are the TDP values?▾
The L40 lists a 300W TDP. The RTX PRO 6000 lists a 600W TDP. Power budgets must account for this twofold difference.
Which interconnect does each GPU use?▾
The L40 uses PCIe 4.0. The RTX PRO 6000 uses PCIe 5.0. Transfer rates improve with the newer standard.
How does memory bandwidth differ?▾
The L40 provides 864 GB/s. The RTX PRO 6000 provides 1792 GB/s. Batch size potential scales with bandwidth.
What FP32 performance is listed?▾
The L40 lists 90.5 TFLOPS FP32. The RTX PRO 6000 lists 126 TFLOPS FP32. The higher figure accelerates precision calculations.
Which is cheaper to rent, the L40 or the RTX PRO 6000?▾
Cloud rental prices for both the L40 and RTX PRO 6000 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 PRO 6000?▾
The L40 has 48 GB of GDDR6 memory. The RTX PRO 6000 has 96 GB of GDDR7 memory.
Can I find L40 and RTX PRO 6000 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 PRO 6000?▾
The L40 uses the Ada Lovelace architecture (2023) while the RTX PRO 6000 uses Blackwell (2025). The RTX PRO 6000 delivers 2.8x the dense FP16 throughput (503.8 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 PRO 6000. 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 PRO 6000 BLACKWELLEvery 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.