A100 vs L40S
Explore a head to head comparison of specifications, performance, and pricing.
A100
The NVIDIA A100 is a powerful Ampere-based GPU designed for AI training, inference, and high-performance computing workloads.
ManufacturerNVIDIA
GPU ArchitectureAmpere
Average Price$6.63/hr
GPU VRAM40 GB
Cloud Availability5 clouds
System Memory1800 GB
CPU Cores176
Storage13.6 TB
L40S
The NVIDIA L40S delivers high-performance computing capabilities for AI, machine learning, and data science applications.
ManufacturerNVIDIA
GPU Architecture—
Average Price$4.94/hr
GPU VRAM48 GB
Cloud Availability7 clouds
System Memory1536 GB
CPU Cores142
Storage30.7 TB
See how the A100 & L40S compare
Compare detailed hardware specifications and average pricing for the A100 and L40S.
Compare Hardware Specifications
| A100 | L40S | |
|---|---|---|
| GPU Type | A100 | L40S |
| VRAM per GPU | 40 GB | 48 GB |
| Manufacturer | NVIDIA | NVIDIA |
| Architecture | Ampere | Ada Lovelace |
| Interconnect | PCIe Gen4 or SXM4 | PCIe Gen4 |
| Memory Bandwidth | 1.55 TB/s | 864 GB/s |
| FP16 TFLOPS | 77.97 TFLOPS (4:1) | 91.61 TFLOPS (1:1) |
| CUDA Cores | 6912 | 18176 |
| Tensor Cores | 432 (3rd Gen) | 568 (4th Gen) |
| RT Cores | N/A | 142 (3rd Gen) |
| Base Clock | 765 MHz | 1110 MHz |
| Boost Clock | 1410 MHz | 2520 MHz |
| TDP | 250W-400W | 350W |
| Process Node | TSMC 7nm | TSMC 4N |
| Data Formats | INT8, BF16, FP16, TF32, FP32, FP64 | INT4, INT8, FP8, BF16, FP16, TF32, FP32 |
Compare Average On-Demand Pricing
| A100 | L40S | |
|---|---|---|
| 1 GPU | $1.71 /hr | $1.27 /hr |
| 2 GPUs | $3.91 /hr | $2.60 /hr |
| 4 GPUs | $7.80 /hr | $5.18 /hr |
| 8 GPUs | $13.54 /hr | $8.70 /hr |
Explore A100 & L40S Instances
Browse available instances with A100 and L40S 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.
