L40S vs A40
Explore a head to head comparison of specifications, performance, and pricing.
L40S
The NVIDIA L40S delivers high-performance computing capabilities for AI, machine learning, and data science applications.
A40
The NVIDIA A40 delivers high-performance computing capabilities for AI, machine learning, and data science applications.
L40S vs A40: Which Should You Choose?
Both the L40S and A40 offer 48 GB of VRAM, putting them on equal footing for memory-bound workloads. On FP16 throughput, the L40S delivers 91.61 TFLOPS versus 37.42 TFLOPS on the A40 — 2× faster for mixed-precision training and inference. Memory bandwidth favors the L40S at 0.86 TB/s compared to 0.70 TB/s on the A40, which directly impacts inference latency for memory-bandwidth-bound models. Architecturally, the L40S is built on Ada Lovelace while the A40 uses Ampere, reflecting different generational capabilities and optimizations. On Shadeform, the L40S starts from $0.74/hr versus $1.10/hr for the A40 — 49% more expensive — reflecting the performance premium. The L40S is available across 7 cloud providers on Shadeform compared to 2 for the A40, giving more options for region and pricing flexibility.
L40S — Best Use Cases
- •LLM inference and model serving
- •Image generation and diffusion models
- •Smaller fine-tuning runs
- •Cost-efficient GPU compute
Choose L40S when:
- ✓Cost efficiency is your primary concern
- ✓You are training large models or running high-throughput inference
- ✓You need flexibility across multiple cloud providers or regions
A40 — Best Use Cases
- •General-purpose deep learning training
- •Fine-tuning models up to 13B parameters
- •AI inference at moderate throughput
- •Computer vision and NLP workloads
Choose A40 when:
- ✓Maximum performance justifies the higher cost
- ✓Your workload does not require peak FP16 throughput
- ✓Your preferred provider already has availability
See how the L40S & A40 compare
Compare detailed hardware specifications and average pricing for the L40S and A40.
Compare Hardware Specifications
| L40S | A40 | |
|---|---|---|
| GPU Type | L40S | A40 |
| VRAM per GPU | 48 GB | 48 GB |
| Manufacturer | NVIDIA | NVIDIA |
| Architecture | Ada Lovelace | Ampere |
| Interconnect | PCIe Gen4 | PCIe Gen4 |
| Memory Bandwidth | 864 GB/s | 696 GB/s |
| FP16 TFLOPS | 91.61 TFLOPS (1:1) | 37.42 TFLOPS (1:1) |
| CUDA Cores | 18176 | 10752 |
| Tensor Cores | 568 (4th Gen) | 336 (3rd Gen) |
| RT Cores | 142 (3rd Gen) | 84 (2nd Gen) |
| Base Clock | 1110 MHz | 1125 MHz |
| Boost Clock | 2520 MHz | 1740 MHz |
| TDP | 350W | 300W |
| Process Node | TSMC 4N | TSMC 8nm |
| Data Formats | INT4, INT8, FP8, BF16, FP16, TF32, FP32 | INT8, BF16, FP16, TF32, FP32 |
Compare Average On-Demand Pricing
| L40S | A40 | |
|---|---|---|
| 1 GPU | $1.29 /hr | $1.48 /hr |
| 2 GPUs | $2.69 /hr | $2.20 /hr |
| 4 GPUs | $5.37 /hr | $5.92 /hr |
| 8 GPUs | $9.37 /hr | $8.80 /hr |
Frequently Asked Questions: L40S vs A40
The main differences are FP16 throughput (91.61 vs 37.42 TFLOPS), architecture (Ada Lovelace vs Ampere). The L40S uses the Ada Lovelace architecture while the A40 is based on Ampere, giving each GPU different generational capabilities.
The L40S is generally better for large language model training due to its higher throughput and 48 GB of VRAM, which allows fitting larger models or larger batch sizes in a single pass. For smaller models or fine-tuning tasks where cost matters more, both GPUs can be effective.
On Shadeform, the L40S is available from $0.74/hr. The A40 starts from $1.10/hr. Prices vary by provider, region, and contract length. Reserved commitments can reduce hourly costs significantly compared to on-demand pricing.
Based on TFLOPS per dollar, the L40S offers better raw compute value at current Shadeform on-demand rates. However, the best choice depends on your specific workload — if you need the extra VRAM or throughput of the A40, paying the premium may be justified by faster job completion and lower total cost.
The L40S is currently available across 7 cloud providers on Shadeform's network, compared to 2 for the A40. Shadeform lets you deploy either GPU across all available providers from a single platform, so you can always find available capacity without manually checking each cloud.
Mixing different GPU types in a single training cluster is generally not recommended, as it creates performance bottlenecks where faster GPUs wait for slower ones. For best results, use a homogeneous cluster of either L40S or A40. Shadeform supports on-demand clusters of up to 64 GPUs of the same type with no commitment required.
Explore L40S & A40 Instances
Browse available instances with L40S and A40 GPUs. Filter by provider, availability, and more to find the perfect instance for your needs.
Explore more GPU comparisons
Select any two GPUs to compare their specifications and explore pricing across providers.
