GPU cloud / L40 vs L40S
L40 vs L40S for inference
VRAM: L40 48 GB; L40S 48 GB. 70B 4-bit estimated memory with 20% headroom: 42.0 GB. Throughput depends on model and workload; enter a measured rate in the cost calculator.
| GPU | Provider | VRAM | GPU count | USD/hour | $/GB/hr | Billing | Type | Verified | Source |
|---|---|---|---|---|---|---|---|---|---|
| L40 | runpod | 48 GB | 1 | $0.82 | $0.017 | per-second | on-demand | 2026-09-26 | Official price ↗ |
| L40 | hyperstack | 48 GB | 1 | $1.00 | $0.021 | per-minute | on-demand | 2026-09-26 | Official price ↗ |
| L40S | runpod | 48 GB | 1 | $1.09 | $0.023 | per-second | on-demand | 2026-09-26 | Official price ↗ |
| L40S | modal | 48 GB | 1 | $1.95GPU only | $0.041 | per-second | on-demand | 2026-09-26 | Official price ↗ |
Each price has an official source and verification date. Rates and availability change; affiliate links, if added later, will be marked sponsored.