GPU Comparison

NVIDIA L40SvsNVIDIA H200

Detailed specifications, performance benchmarks, and pricing comparison to help you choose the right GPU for your AI workloads.

NVIDIA

NVIDIA L40S

Ada Lovelace · 2023

Faster
VRAM48 GB GDDR6
FP3291.6 TFLOPS
FP16183 TFLOPS
Bandwidth864 GB/s
TDP350W
Price$0.85/hr
NVIDIA

NVIDIA H200

Hopper · 2023

VRAM141 GB HBM3e
FP3267 TFLOPS
FP16134 TFLOPS
Bandwidth4800 GB/s
TDP700W
Price$2.25/hr

Specifications · Comparison

Side by side specs.

SpecNVIDIA L40SNVIDIA H200
ArchitectureAda LovelaceHopper
VRAM48 GB141 GB+66%
Memory TypeGDDR6HBM3e
Memory Bandwidth864 GB/s4800 GB/s+82%
FP32 Performance91.6 TFLOPS+36.7%67 TFLOPS
FP16 Performance183 TFLOPS+36.6%134 TFLOPS
INT8 Performance733 TOPS2680 TOPS+72.6%
TDP350W700W
Form FactorPCIeSXM
Price (avg/hr)$0.85$2.25

Performance · Analysis

Performance breakdown.

Compute (FP32)

Raw single-precision floating point throughput

NVIDIA L40S
91.6TFLOPSWinner
NVIDIA H200
67TFLOPS

NVIDIA L40S is 36.7% faster

Training (FP16)

Half-precision performance for deep learning training

NVIDIA L40S
183TFLOPSWinner
NVIDIA H200
134TFLOPS

NVIDIA L40S is 36.6% faster

Inference (INT8)

Integer performance for model inference workloads

NVIDIA L40S
733TOPS
NVIDIA H200
2680TOPSWinner

NVIDIA H200 is 72.6% faster

Memory Bandwidth

Data transfer rate between memory and compute units

NVIDIA L40S
864GB/s
NVIDIA H200
4800GB/sWinner

NVIDIA H200 is 82% faster

Best Compute

NVIDIA L40S

Most Memory

NVIDIA H200

Best Training

NVIDIA L40S

Best Value

NVIDIA L40S

Pricing · Cost

Cost comparison.

Hourly

NVIDIA L40S
$0.85/hr
NVIDIA H200
$2.25/hr

Save $1.40 with NVIDIA L40S

Daily

NVIDIA L40S
$20.40/day
NVIDIA H200
$54.00/day

Save $33.60 with NVIDIA L40S

Monthly

NVIDIA L40S
$612.00/mo
NVIDIA H200
$1620.00/mo

Save $1008.00 with NVIDIA L40S

Use Cases · Workloads

Best for your workload.

NVIDIA

NVIDIA L40S

AI Inference
Graphics Rendering
Video Processing
NVIDIA

NVIDIA H200

LLM Training
LLM Inference
Generative AI
HPC

Platform · Benefits

Why Runcrate.

Instant Deployment

Get your GPU instance running in minutes with pre-configured AI environments. No setup complexity.

Pay Per Hour

Only pay for the compute you actually use. Prepaid credits with transparent, per-hour billing.

Reliable Infrastructure

Enterprise-grade reliability with automatic failover and data persistence across sessions.

FAQ · Questions

Common questions.

Start Building Today

Deploy NVIDIA L40S or NVIDIA H200

Get started with GPU cloud computing in minutes. No setup complexity, no long-term commitments.

No credit card required
Pay-per-hour billing
Cancel anytime