NVIDIA A16 (64GB GDDR6)
- 64GB GDDR6
- Memory
- 800GB/s
- Memory bandwidth
- Q2 2021
- Released
Price history
What it costs to rent a NVIDIA A16
The NVIDIA A16 is an Ampere-architecture inference NVIDIA GPU with 64GB of GDDR6 memory and 800 GB/s of memory bandwidth, released Q2 2021. It is built for inference, fine-tuning and mixed production workloads.
Renting one currently costs between $0.47 and $0.56 per GPU-hour across the 3 cloud providers we track, with a median of $0.52. The cheapest live rate is $0.47/hr from Vultr (On-demand). All rates below are normalised to a single GPU per hour so providers with multi-GPU nodes compare like-for-like.
Where to rent the A16
How we rank
The median is one provider, one vote: each provider contributes the median of its own on-demand listings, then the headline is the median across providers — so no single marketplace or hyperscaler sets the price alone. Below two providers we show the range instead.
Default order is relevance, weighed the way a buyer would: price per GPU first, lightly blended with total node cost; on-demand preferred over spot and reserved when prices are close; established clouds edged above marketplaces; in-stock, recently-checked offers above stale ones; and no single provider is allowed to crowd the top. Click a column to sort by the raw numbers. No paid placements — ranking is never sold.
| Provider | Tier | Config | Total VRAM | Billing | $ / GPU / hr | Total / hr | Availability | Go to provider |
|---|---|---|---|---|---|---|---|---|
 Vultr | Enterprise | 2× A16 | 128GB | On-demand | $0.47 | $0.94 | Unknown | Rent |
 Sesterce | GPU cloud | 2× A16 | 128GB | On-demand | $0.56 | $1.12 | In stock | Rent |
| Vultr | Enterprise | 4× A16 | 256GB | On-demand | $0.47 | $1.88 | Unknown | Rent |
 Runcrate | Marketplace | from A16 | — | On-demand | $0.56 | — | Unknown | Rent |
| Vultr | Enterprise | 8× A16 | 512GB | On-demand | $0.47 | $3.77 | Unknown | Rent |
Technical specifications
- Memory
- 64 GB GDDR6
- Memory bandwidth
- 800 GB/s
- Architecture
- Ampere
- Board power (TDP)
- 250 W
- Released
- Q2 2021
- Class
- Inference
- Cloud providers
- 3 tracked
- Price range
- $0.47 – $0.56 / GPU / hr
Other inference cards
NVIDIA A10SNAPSHOT 2026-08-23T14:41:38.069348+00:00 · BACK TO THE FULL INDEX