P40 vs RTX 4090: Specs, VRAM & Price
Short answer: choose the RTX 4090 when your workload uses FP8 quantized inference or serving. Choose the P40 when your workload is BF16/FP32-only and FP8 buys you nothing.
Both the P40 and the RTX 4090 ship with 24 GB of VRAM.
You can rent both by the hour, no purchase required. P40 from $0.173/GPU/hr; RTX 4090 from $0.374/GPU/hr. The P40 is 54% cheaper at the entry rate.
P40
Good for inference workloads on older-generation hardware
RTX 4090
Good for inference and light fine-tuning workloads
Last updated: 2026-10-10 20:52:29 UTCRefreshes hourly
Specs side by side
| Spec | P40 | RTX 4090 |
|---|---|---|
| VRAM | 24 GB | 24 GB |
| Memory bandwidth | – | 1,008 GB/s |
| Architecture | Pascal | Ada Lovelace |
| Compute capability | 6.1 | 8.9 |
| Precisions in hardware | FP32, FP16 | FP32, FP16, BF16, FP8, INT4 |
| Max board power (TDP) | – | 450W |
| Form factor | PCIe | PCIe 4.0 x16 |
| Regions | 1 | 3 |
On-demand price
| Rate | P40 | RTX 4090 |
|---|---|---|
| Lowest per GPU/hr | $0.173/GPU/hr (cheapest overall) | $0.761/GPU/hr |
Which is better for AI: P40 or RTX 4090?
Choose the RTX 4090 when your workload uses FP8 quantized inference or serving. Choose the P40 when your workload is BF16/FP32-only and FP8 buys you nothing.
P40 vs RTX 4090: common questions
Is the P40 or the RTX 4090 better for AI?
Short answer: choose the RTX 4090 when your workload uses FP8 quantized inference or serving. Choose the P40 when your workload is BF16/FP32-only and FP8 buys you nothing.
Is the P40 or the RTX 4090 cheaper to rent?
On Aquanode's live marketplace the P40 starts at $0.173/GPU/hr (median $0.173/GPU/hr) and the RTX 4090 starts at $0.374/GPU/hr (median $0.757/GPU/hr). The P40 is the cheaper of the two at the entry rate, by 54%.
What is the difference between the P40 and the RTX 4090?
Both cards report 24 GB of VRAM; the P40 is a Pascal part and the RTX 4090 is Ada Lovelace (compute capability 6.1 vs 8.9); only the RTX 4090 supports BF16, FP8, INT4 compute. On price, the P40 lists from $0.173/GPU/hr and the RTX 4090 from $0.374/GPU/hr.
How widely available are the P40 and the RTX 4090?
The P40 is listed in 1 region and the RTX 4090 in 3 regions right now.
How much does 1,000 GPU-hours cost on the P40 vs the RTX 4090?
At the lowest rates listed today, 1,000 GPU-hours costs $173 on the P40 and $374 on the RTX 4090, a difference of $201 for the same runtime. Rates are per GPU per hour and update hourly.
How much VRAM does the P40 have compared to the RTX 4090?
Both the P40 and the RTX 4090 ship with 24 GB of VRAM.
How this comparison is calculated
Every price is normalized to a per-GPU hourly rate using the same pipeline as every other pricing surface on Aquanode, and only the cheapest qualifying offer per provider is shown. A dash means that provider does not currently list that GPU.
Architecture, compute capability and supported precisions come from each vendor's published datasheet for that generation, not from the marketplace feed. This page regenerates at most once per hour.
Memory bandwidth, tensor TFLOPS, NVLink/interconnect and max board power are the same verified-from-datasheet figures shown on each model's own P40 page and RTX 4090 page, which link the primary vendor source for that model. A dash here means Aquanode hasn't verified that figure from a primary source yet, never a guess.
Go further
Check what fits in each card's memory with the P40 VRAM calculator and the RTX 4090 VRAM calculator, or browse every model by generation in the GPU index.
More P40 comparisons
More RTX 4090 comparisons
Related reading: H100 pricing and specs, H100 vs H200, A100 vs H100, H100 and H200: SXM vs NVL vs PCIe, and The best GPUs for AI, ranked.
