Specifications Compared
| Spec | A30 | L40S |
|---|---|---|
| TDP | 165W | 350W |
| VRAM | 24 GB | 48 GB |
| CUDA Cores | 3,584 | 18,176 |
| FP8 (dense) | Not published | 733 TFLOPS |
| Memory Type | HBM2 | GDDR6 |
| Architecture | Ampere | Ada Lovelace |
| FP16 (dense) | 165 TFLOPS | 362.05 TFLOPS |
| Form Factors | PCIe | PCIe |
| INT8 (dense) | 330 TOPS | 733 TOPS |
| Interconnect | NVLink, PCIe 4.0 | PCIe 4.0 |
| Tensor Cores | 224 | 568 |
| FP32 Performance | 10.3 TFLOPS | 91.6 TFLOPS |
| FP64 Performance | 5.2 TFLOPS | 1.4 TFLOPS |
| Memory Bandwidth | 933 GB/s | 864 GB/s |
| FP8 (with sparsity) | Not published | 1,466 TFLOPS |
| FP16 (with sparsity) | 330 TFLOPS | 733 TFLOPS |
| INT8 (with sparsity) | 661 TOPS | 1,466 TOPS |
Performance Analysis
The L40S delivers dense FP16 performance of 362.05 TFLOPS compared to the A30 dense FP16 performance of 165 TFLOPS which indicates greater throughput for mixed precision workloads on the L40S. With sparsity the L40S reaches 733 TFLOPS in FP16 while the A30 reaches 330 TFLOPS in FP16 so the ratio remains consistent when comparing like figures. The A30 memory bandwidth of 933 GB per second exceeds the L40S bandwidth of 864 GB per second and this difference can limit batch sizes on the L40S despite its doubled 48 GB capacity relative to the A30 24 GB capacity. FP32 performance on the L40S at 91.6 TFLOPS exceeds the A30 figure of 10.3 TFLOPS by a wide margin and this gap influences training speed for precision sensitive operations.
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.
A30
A30 is not offered on-demand by any provider we track right now. See the A30 rental page for last-seen listed prices and a price alert.
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 | 8 | $1.09 | $8.72 | Deploy |
| Lyceum | Europe | 1 | $1.99 | — | Deploy |
3 providers in stock, 15 offers (cheapest per provider shown). All L40S offers, price history and alerts
Notify me when A30 drops below a price
One email when the cheapest in-stock on-demand price per GPU-hour falls below your threshold.
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 A30
The A30 suits deployments that prioritize lower TDP of 165 watts and NVLink connectivity for multi GPU scaling. Its 933 GB per second bandwidth supports efficient data movement in bandwidth constrained setups where the 24 GB capacity meets workload needs without excess power draw.
When to Choose the L40S
The L40S suits deployments that require 48 GB capacity and dense FP16 performance of 362.05 TFLOPS for larger models. Its FP32 performance of 91.6 TFLOPS accelerates single precision tasks where the higher TDP of 350 watts remains acceptable.
Use Cases
The L40S provides 48 GB capacity and dense FP16 performance of 362.05 TFLOPS that exceed A30 figures.
The L40S delivers higher dense FP16 performance of 362.05 TFLOPS and double the memory capacity of the A30.
The L40S 48 GB capacity and FP32 performance of 91.6 TFLOPS support larger fine tuning batches than the A30.
The L40S offers 48 GB capacity that accommodates larger diffusion models beyond the A30 24 GB limit.
The A30 TDP of 165 watts and NVLink support enable efficient scaling in power sensitive scientific clusters.
Frequently Asked Questions
What is the memory difference between A30 and L40S?▾
The A30 provides 24 GB HBM2 memory while the L40S provides 48 GB GDDR6 memory.
How does FP16 performance compare between these GPUs?▾
The A30 delivers 165 TFLOPS dense FP16 and the L40S delivers 362.05 TFLOPS dense FP16.
Does the A30 support NVLink?▾
The A30 supports NVLink interconnect in addition to PCIe 4.0 while the L40S supports PCIe 4.0 only.
What are the TDP ratings for A30 and L40S?▾
The A30 TDP is 165 watts and the L40S TDP is 350 watts.
Which GPU has higher FP32 performance?▾
The L40S has FP32 performance of 91.6 TFLOPS compared to 10.3 TFLOPS on the A30.
How does memory bandwidth differ?▾
The A30 provides 933 GB per second bandwidth and the L40S provides 864 GB per second bandwidth.
Which is cheaper to rent, the A30 or the L40S?▾
Cloud rental prices for both the A30 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 A30 have compared to the L40S?▾
The A30 has 24 GB of HBM2 memory. The L40S has 48 GB of GDDR6 memory.
Can I find A30 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 A30 and the L40S?▾
The A30 uses the Ampere architecture (2021) while the L40S uses Ada Lovelace (2023). The L40S delivers 2.2x the dense FP16 throughput (362.05 vs 165 TFLOPS, both without sparsity) while the A30 has 1.1x 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 A30 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 A30Every 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.