RTX-3090-24GB vs RTX-4080-16GB
RTX-3090-24GB is the cheaper of the two: $0.09/hr at Salad, against $0.3/hr for RTX-4080-16GB at GPUhub — 3.3× the price.
Cheapest on each
Aligned facts
Same sheet, same order, both cards — including the gaps.
| Attribute | RTX-3090-24GB | RTX-4080-16GB |
|---|---|---|
| VRAM | 24 GB▲ | 16 GB |
| Bandwidth | ○ no answer | ○ no answer |
| FP16 | ○ no answer | ○ no answer |
| FP8 | ○ no answer | ○ no answer |
| TDP | ○ no answer | 320 W |
| NVLink | ○ no answer | ○ no answer |
| Architecture | Ampere | Ada Lovelace |
| 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 | RTX-3090-24GB | RTX-4080-16GB |
|---|---|---|
| RunPod | $0.502026-10-27 | $0.502026-10-27 |
| Salad | $0.092026-10-26 | ○ no answer |
| Theta EdgeCloud | $0.142026-10-26 | ○ no answer |
| TensorDock | $0.202026-10-26 | ○ no answer |
| Lium | $0.252026-10-27JSON | ○ no answer |
| GPUhub | ○ no answer | $0.302026-10-26 |
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