Specifications Compared
| Spec | L40S | MI355X |
|---|---|---|
| TDP | 350W | 1400W |
| VRAM | 48 GB | 288 GB |
| CUDA Cores | 18,176 | Not published |
| FP4 (dense) | Not published | 10,100 TFLOPS |
| FP8 (dense) | 733 TFLOPS | 5,000 TFLOPS |
| Memory Type | GDDR6 | HBM3e |
| Architecture | Ada Lovelace | CDNA 4 |
| FP16 (dense) | 362.05 TFLOPS | 2,500 TFLOPS |
| Form Factors | PCIe | OAM |
| INT8 (dense) | 733 TOPS | 5,000 TOPS |
| Interconnect | PCIe 4.0 | Infinity Fabric, PCIe 5.0 |
| Tensor Cores | 568 | Not published |
| FP32 Performance | 91.6 TFLOPS | 157.3 TFLOPS |
| FP64 Performance | 1.4 TFLOPS | 78.6 TFLOPS |
| Memory Bandwidth | 864 GB/s | 8,000 GB/s |
| FP8 (with sparsity) | 1,466 TFLOPS | 10,100 TFLOPS |
| FP16 (with sparsity) | 733 TFLOPS | 5,000 TFLOPS |
| INT8 (with sparsity) | 1,466 TOPS | 10,100 TOPS |
Performance Analysis
Dense FP16 performance reaches 362.05 TFLOPS on the L40S and 2500 TFLOPS on the MI355X. This difference determines training iteration rates for workloads that rely on dense FP16 arithmetic. The MI355X also provides 5000 TFLOPS FP16 with sparsity against 733 TFLOPS FP16 with sparsity on the L40S. FP32 throughput of 157.3 TFLOPS on the MI355X versus 91.6 TFLOPS on the L40S further separates the GPUs in precision critical paths. Memory bandwidth of 8000 GB/s on the MI355X permits larger batch sizes than the 864 GB/s available on the L40S during inference passes that move large activation tensors.
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.
L40S
| Provider | Region | GPUs | Per GPU / hr | Instance / hr | Deploy |
|---|---|---|---|---|---|
| Massed Compute | us-central-2 | 1 | $0.97 | — | Deploy |
| QuantaCloud | us-midwest-2 | 1 | $1.09 | — | Deploy |
| RunPod | global | 1 | $1.09 | — | Deploy |
| Lyceum | Europe | 2 | $1.99 | $3.98 | Deploy |
4 providers in stock, 7 offers (cheapest per provider shown). All L40S offers, price history and alerts
MI355X
MI355X is not offered on-demand by any provider we track right now. See the MI355X rental page for last-seen listed prices and a price alert.
Notify me when L40S drops below a price
One email when the cheapest in-stock on-demand price per GPU-hour falls below your threshold. Cheapest right now: $0.97/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 L40S
The L40S fits deployments that require a 350W TDP and standard PCIe slots. Its 48 GB GDDR6 capacity suffices for models that remain within that limit while maintaining 362.05 TFLOPS dense FP16. Organizations that prioritize lower power draw over peak throughput select the L40S for inference or fine tuning tasks that fit these constraints.
When to Choose the MI355X
The MI355X accommodates models that require 288 GB HBM3e capacity and 8000 GB/s bandwidth. Its 2500 TFLOPS dense FP16 supports faster execution of large scale training and inference compared with the L40S. Workloads that benefit from Infinity Fabric interconnect and high memory throughput select the MI355X.
Use Cases
The MI355X supplies 2500 TFLOPS dense FP16 and 288 GB VRAM which exceed the L40S figures of 362.05 TFLOPS dense FP16 and 48 GB VRAM.
The MI355X provides 8000 GB/s bandwidth and 5000 TFLOPS dense FP8 which support larger batches than the L40S at 864 GB/s and 733 TFLOPS dense FP8.
The MI355X 288 GB HBM3e capacity handles parameter updates at 2500 TFLOPS dense FP16 while the L40S remains limited to 48 GB GDDR6.
The L40S 350W TDP and PCIe form factor suit image generation workloads that fit within 48 GB GDDR6 at 362.05 TFLOPS dense FP16.
The L40S delivers 91.6 TFLOPS FP32 at 350W TDP for simulations that do not require the 1400W TDP of the MI355X.
Frequently Asked Questions
What is the memory bandwidth of the MI355X?▾
The MI355X provides 8000 GB/s memory bandwidth. The L40S provides 864 GB/s memory bandwidth.
What dense FP16 performance does each GPU deliver?▾
The L40S delivers 362.05 TFLOPS dense FP16. The MI355X delivers 2500 TFLOPS dense FP16.
What TDP ratings apply to the L40S and MI355X?▾
The L40S has a 350W TDP. The MI355X has a 1400W TDP.
Which interconnect does the MI355X support?▾
The MI355X supports Infinity Fabric and PCIe 5.0. The L40S supports PCIe 4.0.
What FP32 performance is listed for each GPU?▾
The L40S lists 91.6 TFLOPS FP32. The MI355X lists 157.3 TFLOPS FP32.
Which is cheaper to rent, the L40S or the MI355X?▾
Cloud rental prices for both the L40S and MI355X 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 L40S have compared to the MI355X?▾
The L40S has 48 GB of GDDR6 memory. The MI355X has 288 GB of HBM3e memory.
Can I find L40S and MI355X 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 L40S and the MI355X?▾
The L40S uses the Ada Lovelace architecture (2023) while the MI355X uses CDNA 4 (2025). The MI355X delivers 6.9x the dense FP16 throughput (2,500 vs 362.05 TFLOPS, both without sparsity) and 9.3x 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 L40S and the MI355X. 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 L40SEvery current offer by provider, daily price history and a price alert.
- Rent MI355XEvery 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.