Specifications Compared
| Spec | H100 NVL | L40S |
|---|---|---|
| TDP | 700W | 350W |
| VRAM | 94 GB | 48 GB |
| CUDA Cores | 16,896 | 18,176 |
| FP8 (dense) | 1,979 TFLOPS | 733 TFLOPS |
| Memory Type | HBM3 | GDDR6 |
| Architecture | Hopper | Ada Lovelace |
| FP16 (dense) | 989 TFLOPS | 362.05 TFLOPS |
| Form Factors | NVL (PCIe card, NVLink bridged) | PCIe |
| INT8 (dense) | 1,979 TOPS | 733 TOPS |
| Interconnect | NVLink bridge, PCIe 5.0 | PCIe 4.0 |
| Tensor Cores | 528 | 568 |
| FP32 Performance | 67 TFLOPS | 91.6 TFLOPS |
| FP64 Performance | 34 TFLOPS | 1.4 TFLOPS |
| Memory Bandwidth | 3,350 GB/s | 864 GB/s |
| FP8 (with sparsity) | 3,958 TFLOPS | 1,466 TFLOPS |
| FP16 (with sparsity) | 1,979 TFLOPS | 733 TFLOPS |
| INT8 (with sparsity) | 3,958 TOPS | 1,466 TOPS |
Performance Analysis
The H100 family shares 989 TFLOPS FP16 dense throughput while the L40S family shares 362.05 TFLOPS FP16 dense throughput. The same families share 67 TFLOPS FP32 on H100 variants and 91.6 TFLOPS FP32 on L40S variants. Memory bandwidth shared at 3350 GB/s across H100 variants supports larger batch sizes than the 864 GB/s shared across L40S variants. FP16 dense figures favor the H100 NVL for training throughput while FP32 figures favor the L40S for certain scientific workloads. Sparsity figures follow the same pattern with H100 family at 1979 TFLOPS FP16 with sparsity versus L40S family at 733 TFLOPS FP16 with sparsity.
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.
H100 NVL
| Provider | Region | GPUs | Per GPU / hr | Instance / hr | Deploy |
|---|---|---|---|---|---|
| Hyperstack | CANADA-1 | 2 | $2.50 | $5.00 | Deploy |
| QuantaCloud | us-midwest-2 | 2 | $2.59 | $5.18 | Deploy |
| Massed Compute | us-central-3 | 1 | $2.73 | — | Deploy |
| Ori | dallas-2 | 8 | $2.90 | $23.20 | Deploy |
| Scaleway | Paris, France (PAR2) | 1 | $3.23 | — | Deploy |
11 providers in stock, 26 offers (cheapest per provider shown). All H100 NVL offers, price history and alerts
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
Notify me when H100 NVL drops below a price
One email when the cheapest in-stock on-demand price per GPU-hour falls below your threshold. Cheapest right now: $2.50/GPU-hr.
QuantaCloud
Comparing H-series providers? We broker across all of them.
Hopper stock changes by the hour and prices differ by provider. If you need 16+ GPUs reserved or a cluster in the next 90 days, we quote H-series or B300 inventory at partner rates: one quote, 24h turnaround.
When to Choose the H100 NVL
The H100 NVL variant suits LLM training runs that require 94 GB HBM3 memory and NVLink bridge connectivity. Its shared 700 W TDP and 3350 GB/s bandwidth enable sustained high batch sizes on Hopper architecture.
When to Choose the L40S
Use Cases
The H100 NVL variant provides 94 GB HBM3 memory and 989 TFLOPS FP16 dense throughput shared by the H100 family.
The H100 NVL variant supports larger batch sizes with 3350 GB/s bandwidth shared by the H100 family.
The H100 NVL variant delivers 1979 TFLOPS FP16 with sparsity shared by the H100 family for efficient updates.
The L40S variant matches 48 GB GDDR6 memory needs at lower 350 W TDP shared by the L40S family.
The L40S variant supplies 91.6 TFLOPS FP32 shared by the L40S family for precision workloads.
Frequently Asked Questions
How does FP16 dense performance compare between these variants?▾
The H100 family shares 989 TFLOPS FP16 dense throughput. The L40S family shares 362.05 TFLOPS FP16 dense throughput.
What interconnect does the H100 NVL variant use?▾
The H100 NVL variant uses NVLink bridge and PCIe 5.0. The L40S variant uses only PCIe 4.0.
What TDP applies to each family?▾
The H100 family shares 700 W TDP. The L40S family shares 350 W TDP.
How does memory bandwidth differ between the families?▾
The H100 family shares 3350 GB/s bandwidth. The L40S family shares 864 GB/s bandwidth.
Which is cheaper to rent, the H100 NVL or the L40S?▾
Cloud rental prices for both the H100 NVL and L40S 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 H100 NVL have compared to the L40S?▾
The H100 NVL has 94 GB of HBM3 memory. The L40S has 48 GB of GDDR6 memory.
Can I find H100 NVL and L40S 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 H100 NVL and the L40S?▾
The H100 NVL uses the Hopper architecture (2022) while the L40S uses Ada Lovelace (2023). The H100 NVL delivers 2.7x the dense FP16 throughput (989 vs 362.05 TFLOPS, both without sparsity) and 3.9x the memory bandwidth of the L40S.
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 H100 NVL and the L40S. 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 H100Every current offer by provider, daily price history and a price alert.
- Rent L40SEvery 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.