Data Center NVIDIA

NVIDIA L4

Ada Lovelace Architecture · 24GB GDDR6 · PCIe

VRAM
24GB
FP16
60.6
TDP
72W
Hardware Price
$2.8k
MSRP: $2.5k
Cloud from
$0.390/hr
10 providers
Cheapest at RunPod →

Quick Insights

Performance/Dollar
21.64 TFLOPS/$k
FP16 performance per $1000
VRAM/Dollar
8.6 GB/$k
VRAM per $1000
vs Data Center Average
-66% perf
FP16 TFLOPS comparison
Cloud Availability
10 providers
from $0.390/hr

Specifications

VRAM 24GB GDDR6
Memory Bandwidth 300 GB/s
FP16 TFLOPS 60.6
Tensor TFLOPS 242.0
FP32 TFLOPS 30.3
TDP 72W
Form Factor PCIe
Architecture Ada Lovelace
NVLink No
Release Date 2023-03

L4 Price and Rental Notes

NVIDIA L4 price searches include used-card pricing, Google Cloud L4 pricing, and low-cost inference. The main opportunity is to clarify when L4 is cheaper than larger GPUs.

NVIDIA L4 price for cloud inference

L4 is usually evaluated for efficient inference, video workloads, and smaller AI models. Compare cloud hourly price, VRAM, and availability against A10, L40S, and RTX 4090 options.

Google Cloud L4 pricing context

Google Cloud is a common L4 reference point, but final cost depends on region, machine type, committed use discounts, and attached CPU or memory. Use per-GPU pricing only as the first filter.

Best fit

Choose L4 for lower-power inference, media processing, and steady production serving where cost efficiency matters more than maximum training speed.

Related: Compare L4 cloud prices L40S higher-performance alternative Inference GPU recommendations

Buy vs Rent Analysis

Buy Hardware
$2.8k
  • One-time cost, unlimited usage
  • Full control over hardware
  • Electricity & cooling costs extra
  • Depreciation over 2-3 years
Best if using >7179 hours total
Rent Cloud GPU
$0.390/hr
  • Pay only for what you use
  • No upfront investment
  • Scale up/down instantly
  • No maintenance required
Best for <7179 hours or variable usage
Breakeven Point
7,179
hours of usage

At $0.390/hr cloud pricing, buying the hardware pays off after 7,179 hours (~299 days or 10.0 months of 24/7 usage).

Usage Monthly Cloud Cost Months to Breakeven
100 hrs/month $39.00 72 months
200 hrs/month $78.00 36 months
500 hrs/month $195.00 15 months

Cloud GPU Pricing

Rent NVIDIA L4 from 10 cloud providers. Prices shown per GPU per hour.

Provider Type Instance GPUs On-Demand Per GPU Spot Availability
RunPod gpu-cloud NVIDIA L4 1x $0.390/hr $0.390/hr Cheapest $0.220/hr (-44%) -
Google Cloud Platform hyperscaler gcp-l4 1x $0.560/hr $0.560/hr $0.223/hr (-60%) -
Amazon Web Services hyperscaler g6e.xlarge 1x $1.86/hr $1.86/hr - -
Amazon Web Services hyperscaler g6e.2xlarge 1x $2.24/hr $2.24/hr - -
Amazon Web Services hyperscaler g6e.12xlarge 4x $10.49/hr $2.62/hr - -
Amazon Web Services hyperscaler g6e.4xlarge 1x $3.00/hr $3.00/hr - -
Amazon Web Services hyperscaler g6e.24xlarge 4x $15.07/hr $3.77/hr - -
Amazon Web Services hyperscaler g6e.48xlarge 8x $30.13/hr $3.77/hr - -
Amazon Web Services hyperscaler g6e.8xlarge 1x $4.53/hr $4.53/hr - -
Amazon Web Services hyperscaler g6e.16xlarge 1x $7.58/hr $7.58/hr - -
Best Spot Deal: Google Cloud Platform offers spot pricing at $0.223/hr (60% off on-demand).

L4 vs Alternatives

Compare NVIDIA L4 with similar GPUs from other brands.

GPU VRAM FP16 TFLOPS Bandwidth Hardware Price Cloud Price
L4 Current 24GB 60.6 300 GB/s $2.8k - -
AMD Radeon RX 7900 XTX AMD 24GB (+0%) 122.0 (+101%) 960 GB/s - - Compare
AMD Radeon RX 7900 XT AMD 20GB (-17%) 104.0 (+72%) 800 GB/s - - Compare
AMD Instinct MI100 AMD 32GB (+33%) 184.6 (+205%) 1.2 TB/s - - Compare

Best Use Cases

No specific use case recommendations for NVIDIA L4 yet.

Browse All Use Cases →

Compare L4

Other NVIDIA GPUs
Alternatives
Add to Comparison Tool

Frequently Asked Questions about L4

L4 hardware and cloud prices vary by seller and region. This page compares the current site data, cloud options, and nearby alternatives so you can judge value instead of relying on one quote.

Yes, L4 is a strong inference GPU for smaller LLMs, embeddings, image workloads, and video pipelines when 24GB VRAM is enough.

The NVIDIA L4 has a market price of approximately $2.8k (MSRP: $2.5k). Cloud rental starts at $0.390/hr. Prices may vary based on retailer, region, and availability.

Yes, the NVIDIA L4 with 24GB VRAM is suitable for many AI/ML workloads. For large language models, you may need multiple GPUs or consider higher-VRAM options like A100 or H100.

The breakeven point is approximately 7,179 hours of usage. Buy if you'll use it more than this; rent for shorter projects or variable workloads. Cloud rental from RunPod starts at $0.390/hr.

With 24GB VRAM and 60.6 FP16 TFLOPS, the NVIDIA L4 can run: Large language models (7B-13B), Stable Diffusion XL, video AI, and professional 3D rendering.

The NVIDIA L4 offers 24GB VRAM and 60.6 FP16 performance at $2.8k. Compare with similar GPUs using our comparison tool above. Key factors: VRAM for model size, TFLOPS for speed, and price for budget.