NVIDIA · Ada Lovelace

L4 24 GB

A low-power PCIe inference accelerator with 24 GB of GDDR6 memory, commonly offered for model serving, video processing, and fractional or single-GPU cloud instances.

Profile checked · Primary source ↗

Memory
24 GB
Bandwidth
300 GB/s
Offers
4

Available capacity

Observed rental offers

GPU / providerBilling & commitmentPer GPUInstance totalStock & regionChecked / actions
L4 24 GBGoogle Cloudg2-standard-4 Spot · 24 GB per GPU HourlySpot / interruptibleMinimum term unverifiedSpot VM capacity is interruptible. USD 0.4241/hr per GPU USD 0.4241/hr · 1 GPU Stock not verifiedSelected Google Cloud region Check current offer Details & price history
L4 24 GBRunpodCommunity Cloud Pod · 24 GB per GPU HourlyOn-demandMinimum term unverified Starting priceUSD 0.44/hr per GPU USD 0.44/hr · 1 GPU Stock not verifiedCommunity Cloud Check current offer Details & price history
L4 24 GBRunpodSecure Cloud Pod · 24 GB per GPU HourlyOn-demandMinimum term unverified USD 0.49/hr per GPU USD 0.49/hr · 1 GPU Stock not verifiedSecure Cloud Check current offer Details & price history
L4 24 GBGoogle Cloudg2-standard-4 · 24 GB per GPU HourlyOn-demandMinimum term unverified USD 0.7068/hr per GPU USD 0.7068/hr · 1 GPU Stock not verifiedSelected Google Cloud region Check current offer Details & price history

Prices and availability can change. Confirm the current offer with the provider.

Measured performance

Inference benchmarks

Model GPU setup Engine Quant. Workload Output tok/s Evidence
No benchmark records have been supplied yet.