GPU cloud / A100 40GB vs A100 80GB
A100 40GB vs A100 80GB for inference
VRAM: A100 40GB 40 GB; A100 80GB 80 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 |
|---|---|---|---|---|---|---|---|---|---|
| A100 80GB | hyperstack | 80 GB | 1 | $1.35 | $0.017 | per-minute | on-demand | 2026-09-26 | Official price ↗ |
| A100 80GB | runpod | 80 GB | 1 | $1.59 | $0.020 | per-second | on-demand | 2026-09-26 | Official price ↗ |
| A100 80GB | tensordock | 80 GB | 1 | from $1.80 | $0.022 | hourly | on-demand | 2026-09-26 | Official price ↗ |
| A100 80GB | modal | 80 GB | 1 | $2.50GPU only | $0.031 | per-second | on-demand | 2026-09-26 | Official price ↗ |
| A100 80GB | ovhcloud | 80 GB | 1 | $3.07 | $0.038 | hourly | on-demand | 2026-09-26 | Official price ↗ |
| A100 80GB | digitalocean | 80 GB | 1 | $3.18 | $0.040 | hourly | on-demand | 2026-09-26 | Official price ↗ |
| A100 40GB | lambda | 40 GB | 1 | $1.99 | $0.050 | per-minute | on-demand | 2026-09-26 | Official price ↗ |
| A100 40GB | modal | 40 GB | 1 | $2.10GPU only | $0.052 | 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.