DallasTexas · US-TX-1
190cards in catalogA dedicated NVIDIA L4 with 24 GB GDDR6 ECC, 8 vCPU, 64 GB system RAM, and 1 TB local NVMe per card.
Node pricing
The product model allocates each GPU to one account for the complete term. Adding cards to a node applies the catalog volume discount to every card.
| Node | Total VRAM | 7 days | 30 days | Discount |
|---|---|---|---|---|
| 1× L4 | 24 GB | $70 | $250 | 0% |
| 2× L4 | 48 GB | $133 | $475 | 5% |
| 4× L4 | 96 GB | $258 | $920 | 8% |
| 8× L4 | 192 GB | $504 | $1,800 | 10% |
Regional inventory
Ready-to-run images
Workload fit
A 24 GB option in the catalog for compact inference and video-processing workloads with modest memory requirements.
Your catalog configuration pairs 24 GB GPU memory with 64 GB host RAM and 1 TB local NVMe per card.
Confirm sustainable concurrency and codec or framework compatibility. Avoid choosing from VRAM alone when throughput or latency is the actual target.
Use $70 for a 7-day pilot, or $250 for a 30-day allocation after validating the workload. Options are additional.