NVIDIA Ada Lovelace

NVIDIA L4

L4 is a low-profile PCIe accelerator optimized for media, inference, and edge deployments.

Launch year
2023
Memory
24 GB GDDR6
Memory bandwidth
300 GB/s
Peak FP16 / FP32
61 TFLOPS · 31 TFLOPS

Market snapshot

$0.12 /hr

Range $0.12 – $43.70

Catalog coverage

1309 live offerings

Across 6 providers · 119 regions

  • Dual NVENC/NVDEC
  • 75 W single-slot
  • Edge-friendly footprint
NVIDIA L4 render

Last refreshed Oct 20, 2025, 2:01 AM

Performance snapshot

Normalized versus NVIDIA A100 (=1.0). Values use public reference benchmarks for training and inference workloads.

  • AI Inference (FP16)×0.35
  • Media Encoding×0.55
  • Power efficiency×0.70

Provider availability

Price bands per provider pulled from the live catalog.

  • Amazon Web Services logoAmazon Web Services438 offers
    $0.12 – $43.70 /hr
  • Datacrunch logoDatacrunch32 offers
    $0.18 – $7.31 /hr
  • Google Cloud logoGoogle Cloud688 offers
    $0.19 – $12.81 /hr
  • RunPod logoRunPod99 offers
    $0.22 – $6.21 /hr
  • Nebius logoNebius12 offers
    $1.55 – $11.01 /hr
  • Oracle Cloud logoOracle Cloud40 offers
    $14.00 – $14.00 /hr

Popular regions

  • us-east-236 offers
  • eu-north-136 offers
  • eu-central-136 offers
  • ap-northeast-236 offers
  • us-east-136 offers
  • us-west-236 offers
  • ap-northeast-136 offers
  • ap-southeast-220 offers

Weighted average price $3.07 /hr · median $1.40