Live Floor
$0.5356
Vast · TR
The NVIDIA L40S is based on the Ada Lovelace architecture with 48 GB of GDDR6 VRAM.
Best live route via Vast · TR
Live Floor
$0.5356
Vast · TR
Average Price
$1.3968
Across 10 live offers
Reliability
96.4%
Based on 10 scored hosts
Last Day Delta
-$0.2544
Latest daily low: 2026-10-13
30-Day Price Trend
Available Offers
Sorted by cheapest hourly rate
| Provider | Price/hr | VRAM | GPUs | Reliability | Region | |
|---|---|---|---|---|---|---|
| Vast | $0.5356 | 45 GB | 1x | 99.9% | TR | View Deal |
| Vast | $0.7348 | 45 GB | 1x | 92.2% | TW | View Deal |
| RunPod | $0.7900 | 48 GB | 1x | 90.0% | -- | View Deal |
| Vast | $0.8015 | 45 GB | 1x | 99.8% | TW | View Deal |
| Vast | $0.8169 | 45 GB | 1x | 99.2% | RO | View Deal |
| Vast | $0.8422 | 45 GB | 1x | 98.2% | KR | View Deal |
| Vast | $1.4681 | 45 GB | 2x | 92.2% | TW | View Deal |
| Vast | $1.6015 | 45 GB | 2x | 99.9% | TW | View Deal |
| Vast | $3.1759 | 45 GB | 4x | 92.8% | SG | View Deal |
| Vast | $3.2015 | 45 GB | 4x | 99.9% | TW | View Deal |
GPU Overview
The NVIDIA L40S is based on the Ada Lovelace architecture with 48 GB of GDDR6 VRAM. It provides datacenter-grade scalability in a versatile form factor, balancing compute performance with power efficiency for AI inference and mixed visual-compute workloads.
With 48 GB of VRAM, the L40S handles Large Language Models (LLM) and fine-tuning of medium-to-large models efficiently. It is well-suited for inference serving, video processing pipelines, and multi-modal AI applications where memory capacity and throughput need to scale across datacenter deployments.