L40S vs RTX A6000

Compare NVIDIA L40S and NVIDIA RTX A6000 specs, performance, and cloud pricing

L40S

48GB

From $0.820/hr

RTX A6000

48GB

From $0.520/hr

Architecture

Ada Lovelace

vs Ampere

FP16 Gap

1.2x

L40S leads

SpecificationL40SRTX A6000
VRAM48 GB48 GB
VRAM TypeGDDR6XGDDR6
FP16 TFLOPS366.5 TFLOPS310 TFLOPS
FP8 TFLOPS733 TFLOPSN/A
Memory Bandwidth864 GB/s768 GB/s
TDP350W300W
InterconnectPCIe Gen4NVLink
ArchitectureAda LovelaceAmpere

Price Comparison

MetricL40SRTX A6000
Cheapest On-Demand$0.820/hr$0.520/hr
Cheapest Spot$0.440/hr$0.390/hr
Providers Available54

Verdict

Best for Training

NVIDIA L40S

366.5 TFLOPS FP16 with 48GB VRAM

Best Value

NVIDIA RTX A6000

596 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

RTX A6000

Starting at $0.520/hr delivers the best TFLOPS per dollar.

Learn More