L40S vs RTX 4090

Compare NVIDIA L40S and NVIDIA RTX 4090 specs, performance, and cloud pricing

L40S

48GB

From $0.820/hr

RTX 4090

24GB

From $0.370/hr

Architecture

Ada Lovelace

vs Ada Lovelace

FP16 Gap

4.4x

L40S leads

SpecificationL40SRTX 4090
VRAM48 GB24 GB
VRAM TypeGDDR6XGDDR6X
FP16 TFLOPS366.5 TFLOPS83 TFLOPS
FP8 TFLOPS733 TFLOPS166 TFLOPS
Memory Bandwidth864 GB/s1.0 TB/s
TDP350W450W
InterconnectPCIe Gen4None
ArchitectureAda LovelaceAda Lovelace

Price Comparison

MetricL40SRTX 4090
Cheapest On-Demand$0.820/hr$0.370/hr
Cheapest Spot$0.440/hr$0.280/hr
Providers Available53

Verdict

Best for Training

NVIDIA L40S

366.5 TFLOPS FP16 with 48GB VRAM

Best Value

NVIDIA L40S

447 TFLOPS per $/hr

Best for Inference

NVIDIA L40S

733 TFLOPS FP8/FP16

Use-Case Recommendations

Large-Scale Training

Training LLMs and large multi-modal models

Winner

L40S

366.5 TFLOPS FP16 with 48GB GDDR6X provides the best training throughput.

Inference at Scale

Deploying models in production for real-time inference

Winner

L40S

733 TFLOPS FP8/FP16 gives superior inference throughput.

Budget-Conscious Workloads

Getting the best performance per dollar

Winner

L40S

Starting at $0.820/hr delivers the best TFLOPS per dollar.

Learn More