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 / provider | Billing & commitment | Per GPU | Instance total | Stock & region | Checked / 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. | ||||||