A100-80GB vs A100-PCIE
A100-PCIE is the cheaper of the two: $0.74/hr at Vast.ai, against $1.43/hr for A100-80GB at Packet·ai — 1.9× the price.
Cheapest on each
Aligned facts
Same sheet, same order, both cards — including the gaps.
| Attribute | A100-80GB | A100-PCIE |
|---|---|---|
| VRAM | ○ no answer | ○ no answer |
| Bandwidth | ○ no answer | ○ no answer |
| FP16 | ○ no answer | ○ no answer |
| FP8 | ○ no answer | ○ no answer |
| TDP | ○ no answer | ○ no answer |
| NVLink | ○ no answer | ○ no answer |
| Architecture | ○ no answer | Ampere |
| Released | ○ no answer | ○ no answer |
A blank is not a zero. Where one card states a figure and the other states none, neither wins the row — the second number is unknown, and ranking an unknown as nothing is how a comparison starts to lie.
Every seller, both cards
One row per seller, cheapest tier, on-demand list prices only. Sellers of both cards lead, cheapest combined rate first.
| Seller | A100-80GB | A100-PCIE |
|---|---|---|
| Packet·ai | $1.432026-10-27 | ○ no answer |
| DeepInfra | $1.492026-10-26 | ○ no answer |
| Oblivus | $1.572026-10-26 | ○ no answer |
| Runcrate | $1.732026-10-26 | ○ no answer |
| Thunder Compute | $1.952026-10-26 | ○ no answer |
| Theta EdgeCloud | $1.992026-10-26 | ○ no answer |
| Leafcloud | $2.082026-10-26 | ○ no answer |
| Vast.ai | ○ no answer | $0.742026-10-27 |
| RunPod | ○ no answer | $1.792026-10-27 |
What this page will not tell you
On-demand list rates only · spot and committed terms priced separately and not mixed in here · no performance-per-dollar figure appears on this page, because it needs a throughput benchmark we do not hold and dividing a price by a vendor’s own TFLOPS claim produces a number that looks authoritative and means nothing