NVIDIA L40S
0
CUDA Cores
48GB
VRAM
864
GB/s
Technical Specifications
0
CUDA Cores
0
Base MHz
0
Boost MHz
48GB GDDR6
384-bit bus
Performance
90
FP32 TFLOPS
180
FP16 TFLOPS
350W
TDP
Cloud Availability
6
Available Instances
$0.96/hr
Starting Price
Detailed Specifications
| Architecture | Ada Lovelace (Unknown) |
| Release Date | 2023-10-01 |
| Launch Price | $2,000.00 |
| Process | 4nm |
| Transistors |
AI Features
Gen 4
Tensor Cores
Enabled
Transformer Engine
Not Supported
Flash Attention
Physical Specifications
Dimensions
10.5in
Length
4.4in
Width
2-slot
Height
About L40S GPU
The NVIDIA L40S is a powerful GPU designed for AI/ML workloads, offering exceptional performance for both training and inference tasks. With 48GB of VRAM and 0 CUDA cores, it provides the memory capacity and computational power needed for modern deep learning models.
Released in 2023, the L40S features Ada Lovelace architecture with advanced AI accelerators including Tensor Cores and Transformer Engine support. This makes it ideal for large language models, computer vision tasks, and generative AI applications.
When considering cloud rental options for the L40S, pricing starts at $0.96/hour from various providers. This GPU offers excellent price-to-performance for AI training workloads, with its high memory bandwidth of 864 GB/s enabling fast data transfer for large datasets.
The L40S features CUDA compute capability 8.9 and is compatible with all major deep learning frameworks including PyTorch, TensorFlow, and JAX. Its 4nm manufacturing process ensures efficient power consumption relative to performance output.
Rent L40S from Our Partners
Get started quickly with these trusted GPU cloud providers. We may earn a commission when you sign up.
External Resources
Learn more about GPUs from these authoritative sources:
Official CUDA programming guide
NVIDIA GPU Specifications →Official NVIDIA GPU specs
TechPowerUp GPU Database →Comprehensive GPU specifications
CUDA Compute Capability Guide →GPU compute capability reference
What You Need to Know About the L40S
Complete Specifications for the NVIDIA L40S
Get detailed technical specifications for the NVIDIA L40S including VRAM capacity of , CUDA core count, Tensor Core count, memory bandwidth, and CUDA compute capability of . This GPU is designed for demanding AI training, inference, and high-performance computing workloads. Understanding these specifications helps you determine whether it is the right fit for PyTorch, TensorFlow, or custom CUDA-based applications.
Compare NVIDIA L40S Cloud Rental Prices per Hour
Find the best cloud rental prices for the NVIDIA L40S across providers like RunPod, Vast.ai, Lambda Labs, and CoreWeave. GPUvec aggregates real-time pricing data so you can compare costs per hour, find available instances, and choose the most cost-effective provider. GPU cloud pricing for this model varies by region and instance type, so comparing multiple options can save significantly on compute costs.
Is the NVIDIA L40S the Right GPU for Your AI Workload?
Learn whether the NVIDIA L40S is the right choice for your specific AI and ML workloads. We cover use cases including large language model training, fine-tuning, inference serving, computer vision, scientific computing, and rendering. Compare its specifications and pricing against other GPUs like the H100, A100, and RTX 5090 to make an informed decision for your infrastructure needs.
Top GPUs for Training and Inference
| Category | Rank 1 | Rank 2 | Rank 3 |
|---|---|---|---|
| Best for Training | NVIDIA H200 | NVIDIA H100 | NVIDIA B200 |
| Best for Inference | NVIDIA A40 | NVIDIA A100 | NVIDIA A10 |
Compare GPU specifications and cloud instances to find the best GPU for your workload.